Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

ux-designer

skill · shubhamsaboo/awesome-llm-appsApache-2.0 licenceAudited 13 Nov 2026 · source 20ad99b9ef42

★ 144,524pushed 1 day agoversion 1.3.0
✕BLOCKGrade F · 28/100 · 25 findings · 20ad99b
144,524repo stars · whole shubhamsaboo/awesome-llm-apps

Is it safe? No — BLOCK, grade F (28/100). We read this skill's source at commit 20ad99b9ef42 and observed filesystem, network and shell access and a hard-coded secret (see the findings). The audit raised 25 findings, 9 critical or high. What it does: Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple models, split work…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “ux-designer (shubhamsaboo/awesome-llm-apps)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/shubhamsaboo/ux-designer

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 9 critical or high findings, starting with “Code injection” in ai_agent_framework_crash_course/google_adk_crash_course/4_tool_using_agent/4_2_function_tools/calculator_agent/tools.py:30. Do not install it without reading them.

3 skills are called “ux-designer”. You are viewing shubhamsaboo/awesome-llm-apps. 3 of them are BLOCK.

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score28/100✕BLOCK F
0 critical9 high15 medium40 low5 info

BLOCK means the audit found something that could harm you or your machine. Grade F is shared by 129 of 18,389 audited skills.

What the source does

  • FilesystemDeclared13 observations
  • NetworkDeclared17 observations
  • ShellDeclared6 observations
  • DependenciesNot pinnedSome versions float
  • SecretsFoundSee the findings; values are never shown

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN3
L1 Static sourceSecrets, path traversal, supply chain, hidden codeFAIL21
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: instruction override, no behavioural pass.

Findings (25)

HIGHCode injectioncode.eval_exec · ai_agent_framework_crash_course/google_adk_crash_course/4_tool_using_agent/4_2_function_tools/calculator_agent/tools.py:30
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
result = eval(safe_expression)
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · generative_ui_agents/ai-mcp-app-builder/apps/threejs-server/src/threejs-app.tsx:152
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
const fn = new Function(
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · generative_ui_agents/ai-mcp-app-builder/apps/web/app/api/copilotkit/route.ts:224
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
"1) exec(\"ss -tlnp 'sport = :3109' | grep -oP 'pid=\\\\K[0-9]+' | head -1 | xargs -r kill; sleep 1\") " +
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · generative_ui_agents/ai-mcp-app-builder/apps/web/app/api/copilotkit/route.ts:483
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
exec(workspaceId, "kill $(lsof -t -i:3109) 2>/dev/null; sleep 1")
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · generative_ui_agents/ai-mcp-app-builder/apps/web/app/api/copilotkit/route.ts:484
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
exec(workspaceId, "npm run dev", background=true)
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHFilesystem / pathfs.credential_store · agent_skills/evals/tools/skill_scanner.py:86
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
"CRED01", "CRITICAL", "Reads SSH key material (SSH dir, id_rsa, id_ed25519)"),  # skillscan:allow
Why
touches a credential store
Fix
—
HIGHNetwork egressnet.env_exfil · agent_skills/evals/tools/skill_scanner.py:85
F-04 Network egressCWE-200 · CWE-319Layer L1
id_rsa ... WebSocket
Why
reads secrets in the same file that sends data out
Fix
—
HIGHHard-coded secretssecret.db_uri · advanced_ai_agents/multi_agent_apps/agent_teams/ai_travel_planner_agent_team/client/.env.example:2
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1
DATA…://…@localhost:5432/tripcraft_ai
Why
No further detail recorded for this rule.
Fix
—
HIGHPrompt injectionprompt.override · generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/references/setup.md:55
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- Developer Mode enabled: Settings → Connectors → Advanced → Developer Mode
Why
asks the agent to drop prior instructions or safety
Fix
remove the instruction
MEDIUMInventory / provenanceinv.binary · generative_ui_agents/ai-financial-coach-agent/docker/Dockerfile.app
F-13 Inventory / provenanceCWE-1104Layer L0
Dockerfile.app
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · generative_ui_agents/generative-ui-starter-project/docker/Dockerfile.app
F-13 Inventory / provenanceCWE-1104Layer L0
Dockerfile.app
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInformation disclosuredisclose.log_secret · agent_skills/first-reader/scripts/feed.py:306
F-12 Information disclosureCWE-209 · CWE-532Layer L1
print(f"reader {r['…']}: READER_FEED={base}/{token}")
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.beacon_words · agent_skills/evals/tools/skill_scanner.py:326
F-04 Network egressCWE-200 · CWE-319Layer L1
add("EXFIL01", "CRITICAL", path, 0,
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.beacon_words · agent_skills/evals/tools/skill_scanner.py:327
F-04 Network egressCWE-200 · CWE-319Layer L1
"Same file both touches credentials/environment and makes network calls — the standard exfiltration shape. Review it line by line.", "")
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.beacon_words · generative_ui_agents/ai-knowledge-explorer/src/lib/example-content.ts:86
F-04 Network egressCWE-200 · CWE-319Layer L1
Agents with tool access can be manipulated through prompt injection. A malicious document could instruct the agent to exfiltrate data or delete files. Sandboxing tool access, validating tool inputs, a
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · advanced_ai_agents/multi_agent_apps/agent_teams/ai_travel_planner_agent_team/backend/api/app.py:49
F-04 Network egressCWE-200 · CWE-319Layer L1
"ALLOWED_ORIGINS", "http://localhost:3000,http://127.0.0.1:3000"
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · advanced_ai_agents/multi_agent_apps/ai_negotiation_battle_simulator/backend/agent.py:417
F-04 Network egressCWE-200 · CWE-319Layer L1
allow_origins=["http://localhost:3000", "http://127.0.0.1:3000"],
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · advanced_ai_agents/single_agent_apps/earnings_call_analyst_agent/live_demo/server.py:78
F-04 Network egressCWE-200 · CWE-319Layer L1
allow_origins=["http://127.0.0.1:4188", "http://localhost:4188"],
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.zero_width · advanced_ai_agents/multi_agent_apps/agent_teams/ai_legal_agent_team/legal_agent_team.py:107
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
st.title("AI Legal Agent Team 👨⚖️")
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.zero_width · advanced_ai_agents/multi_agent_apps/agent_teams/ai_teaching_agent_team/teaching_agent_team.py:12
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
st.set_page_config(page_title="👨🏫 AI Teaching Agent Team", layout="centered")
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.zero_width · advanced_ai_agents/multi_agent_apps/agent_teams/ai_teaching_agent_team/teaching_agent_team.py:120
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
st.title("👨🏫 AI Teaching Agent Team")
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.zero_width · advanced_ai_agents/single_agent_apps/ai_health_fitness_agent/health_agent.py:8
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
page_icon="🏋️♂️",
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.zero_width · advanced_ai_agents/single_agent_apps/ai_health_fitness_agent/health_agent.py:66
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
st.markdown("### 🏋️♂️ Exercise Routine")
Why
No further detail recorded for this rule.
Fix
—
MEDIUMHard-coded secretssecret.slack · advanced_ai_agents/multi_agent_apps/ai_news_and_podcast_agents/readme.md:495
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1
SLAC…
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenanceinv.binary · advanced_ai_agents/multi_agent_apps/ai_news_and_podcast_agents/beifong/tests/english_sample_0.wav
F-13 Inventory / provenanceCWE-1104Layer L0
english_sample_0.wav
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README

Audit 0.4.1 · source sha 20ad99b9ef42 · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishershubhamsaboo GitHub userOwner of the repository this skill is read from
  • Source foldershubhamsaboo/awesome-llm-appsThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict20ad99b9ef42A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple models, split work…

---
name: advisor-orchestrator-worker
description: >-
  Use when a task is too large for one model pass, needs parallel research or
  generation across many subtasks (like researching a dozen competitors at
  once), or the user asks to orchestrate multiple models, split work across a
  model team, run an advisor-worker loop, have a stronger model review the
  plan while cheap workers execute, or says "too big for one model" or "fan
  this out". Not for single-file edits or tasks one model handles in one pass.
license: Apache-2.0
metadata:
  author: "Shubham Saboo"
  version: "1.0.0"
  source: "https://github.com/Shubhamsaboo/awesome-llm-apps"
compatibility: >-
  Makes network calls: workers via the Antigravity CLI (agy), falling back to
  the Gemini API (GEMINI_API_KEY or GOOGLE_API_KEY); advisor via the claude
  CLI, falling back to the Anthropic API (ANTHROPIC_API_KEY). Needs jq. All
  snippets are bash. Runs in any harness that can execute shell commands.
---

# Advisor Orchestrator Worker

You are the Orchestrator of a three-tier model team. You own the hot
path: plan, delegate, verify, synthesize. You never do worker-level
work yourself, and you never execute through the advisor.

**Models are knobs.** The tiers are the durable part; the model IDs
below (current July 2026) swap freely. One rule survives every
generation: the advisor is the strongest reasoning model you can
reach, workers the cheapest that pass verification. Snippets are bash;
on another shell, run them with `bash -c`.

## The team

- **Workers (default: Gemini 3.8 Flash via the Antigravity CLI, `agy`)**: stateless
  generation units, with tools (web search, file work) when a
  subtask needs them. Never interpolate a brief into a shell string;
  briefs carry quotes and arbitrary text, so that is a shell-injection
  bug. Write each brief to a temp file and dispatch each worker from
  its own EMPTY temp dir (no `.antigravity.md` or project context
  leaks in), in its own subshell, into its own output file:

  ```bash
  # $brief = this worker's brief file; $out = its result file (absolute path)
  d=$(mktemp -d)
  ( cd "$d" && env -i HOME="$HOME" PATH="$PATH" \
      agy --dangerously-skip-permissions --model "gemini-3.8-flash" --effort high \
      --print-timeout 5m -p "$(cat "$brief")" \
      > "$out"; s=$?; rm -rf "$d"; exit "$s" ) &
  pids+=($!)
  ```

  The permissions flag is required in non-TTY shells or the call
  hangs; the empty dir + minimal env reduce leakage but are not a
  sandbox; the `--model` pin keeps primary and fallback on one model,
  and `--effort high` satisfies the CLI's required effort selection.
  Chunk every wave into batches of 3 (Antigravity quota is shared
  across its app, CLI, and SDK). Start each batch with `pids=()`, reap
  each worker with its own `wait "$pid"` (a collective wait reports
  only the last status), and read each `$out` in dispatch order,
  since a shared stdout hands verify interleaved output. Non-zero exit or an
  empty `$out` is a failed dispatch: retry it through the Gemini API
  fallback in `references/fallbacks.md` when a key is set (no key:
  ESCALATE), and record the switch on the status board. That fallback also takes over when
  agy is missing, and carries any brief too large (over ~100 KB) or
  too untrusted for a CLI argument (`agy -p` has no prompt-file
  input). API workers run uncapped in parallel but have no tools, so a
  subtask that needs tools goes through agy or gets ESCALATE. Clean up
  all temp files at run end.

- **Advisor (default: Claude Fable 5.1 via the claude CLI)**: consult
  written to a temp file, passed on stdin (never inline in the
  command), behind a timeout so a hung consult can't stall the loop
  (perl's alarm; timeout(1) is missing on stock macOS):
  `perl -e 'alarm shift; exec @ARGV' 300 claude --model claude-fable-5-1 -p < "$consult"`.
  Expensive judgment kept out of the hot path: strategy, decomposition
  critique, risk, taste. Never execution. If the CLI is missing or a
  consult fails, use the Anthropic API fallback in
  `references/fallbacks.md`.

## The loop

1. **Frame.** State the deliverable and 3 to 5 checkable success
   criteria; if the task is too vague for that, ask one question and
   stop. Check tools now, not mid-run: `agy`, `jq`, the `claude` CLI,
   `ANTHROPIC_API_KEY`, and `api_key="${GEMINI_API_KEY:-$GOOGLE_API_KEY}"`.
   Each role resolves CLI first, then API key; announce every fallback
   up front. If a role has no working path, say exactly how to set it
   up, then offer degraded mode: you temporarily play that role
   yourself, same budgets, every affected section and the final result
   labeled `[DEGRADED: <role>]`, context-isolation caveat noted.
   Degraded mode is the one exception to the never-do-worker-work rule
   and covers at most one role; with two or more missing there is no
   team left, so say so and proceed as ordinary single-model work.
2. **Plan.** Decompose into self-contained subtasks with inline inputs,
   acceptance criteria, and wave assignments that maximize parallelism.
3. **Plan review (mandatory advisor consult #1).** Send the plan using
   the format in `references/advisor-consult.md`. Revise. State what
   you changed and what you rejected.
4. **Delegate.** Dispatch each wave using the format in
   `references/worker-brief.md`. Parallel background calls, then wait.
5. **Verify.** Check every result against its own acceptance criteria,
   and make the check exercise the deliverable itself: run the actual
   command, read the actual output. Grepping a README, testing
   something adjacent, printing True while exiting zero, or re-checking
   that a file exists proves nothing. Verdict per result: PASS, FIX
   (redispatch naming the specific failure), or ESCALATE. Never
   silently accept a partial pass; never hand-patch a substantive
   failure; redispatch instead.
6. **Synthesize.** When all subtasks pass, assemble the deliverable.
   Resolve conflicts between worker outputs explici

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 20ad99b

npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/project-graveyard
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
pip install -r requirements.txt

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 20ad99b9ef42 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✕BLOCK F 28 / 100

    first audit · source 20ad99b9ef42

README badge

For maintainers · shows the latest audit

ModelsAtlas: BLOCK FMODELSATLASBLOCK · F
[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/shubhamsaboo/ux-designer/badge.svg)](https://modelsatlas.com/skills/shubhamsaboo/ux-designer/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/shubhamsaboo/ux-designer/badge.svg)](https://modelsatlas.com/skills/shubhamsaboo/ux-designer/)

Questions about ux-designer

What does the ux-designer skill do?
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Is ux-designer safe to install?
No — not without reading the findings first. The audit graded it F (28/100) and found 9 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What can ux-designer access on my machine?
The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: found — see the findings.
Which assistants does ux-designer work with?
Its documentation mentions claude-code, codex, copilot, cursor and openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (20ad99b9ef42), read on 2026-11-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.