Agent skill · Audited from source
replay-ux-research
skill · getsentry/skillsApache-2.0 licenceAudited 14 Nov 2026 · source 417b3e68b04d
Is it safe? No — BLOCK, grade F (48/100). We read this skill's source at commit 417b3e68b04d and observed filesystem, network and shell access and no hard-coded secrets. The audit raised 25 findings, 8 critical or high. What it does: Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or…
Cite
Cite this page
ModelsAtlas. “replay-ux-research (getsentry/skills)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/getsentry/replay-ux-research
Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 8 critical or high findings, starting with “Code injection” in skills/skill-scanner/scripts/scan_skill.py:88. Do not install it without reading them.
2 skills are called “replay-ux-research”. You are viewing getsentry/skills. 2 of them are BLOCK.
- getsentry/skills★ 1.2k✕BLOCK
- getsentry/skills★ 1.1k✕BLOCK
Trust audit
Audit 0.4.1 · source read 14 Nov 2026
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
- FilesystemDeclared1 observation
- NetworkDeclared2 observations
- ShellDeclared3 observations
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | WARN | 2 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | FAIL | 16 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 7 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: instruction override, no behavioural pass.
Findings (25)
HIGHCode injectioncode.eval_exec · skills/skill-scanner/scripts/scan_skill.py:88
(r"\beval\s*\(", "eval() usage", "high"),- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · skills/skill-scanner/scripts/scan_skill.py:89
(r"\bexec\s*\(", "exec() usage", "high"),- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHFilesystem / pathfs.credential_store · skills/skill-scanner/scripts/scan_skill.py:394
"Symlinks can trick agents into reading sensitive files (e.g., ~/.ssh/id_rsa) "
- Why
- touches a credential store
- Fix
- —
HIGHPrompt injectionprompt.override · skills/skill-scanner/references/prompt-injection-patterns.md:11
| Ignore previous instructions | "Ignore all previous instructions and..." | Critical |
- Why
- asks the agent to drop prior instructions or safety
- Fix
- remove the instruction
HIGHPrompt injectionprompt.override · skills/skill-scanner/references/prompt-injection-patterns.md:12
| Disregard prior rules | "Disregard your prior guidelines" | Critical |
- Why
- asks the agent to drop prior instructions or safety
- Fix
- remove the instruction
HIGHPrompt injectionprompt.read_system · skills/skill-scanner/SKILL.md:112
- **Image metadata**: PNG files with text in metadata chunks (tEXt/iTXt) — multimodal LLMs can read hidden instructions from image metadata
- Why
- No further detail recorded for this rule.
- Fix
- —
HIGHPrompt injectionprompt.zero_width · skills/skill-scanner/references/prompt-injection-patterns.md:72
These can be used to split keywords to evade pattern matching (e.g., "ignore" with a zero-width space).
- Why
- invisible characters in instruction text
- Fix
- strip non-printing characters
MEDIUMInventory / provenanceinv.symlink · .agents/skills
.agents/skills
- Why
- link not followed
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · skills/skill-scanner/scripts/scan_skill.py:79
(r"(?i)(requests\.(get|post|put)|urllib\.request|http\.client|aiohttp)\s*\(", "HTTP request (potential exfiltration)", "medium"),- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · skills/skill-scanner/scripts/scan_skill.py:396
"category": "Symlink Exfiltration",
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWInventory / provenanceinv.symlink · CLAUDE.md
CLAUDE.md
- Why
- link not followed
- Fix
- —
LOWNetwork egressnet.metadata_ip · skills/gha-security-review/references/runner-infrastructure.md:70
curl http://169.254.169.254/latest/meta-data/ # Cloud metadata (example of attack vector)
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
LOWNetwork egressnet.metadata_ip · skills/security-review/references/ssrf.md:19
http://169.254.169.254/latest/meta-data/iam/security-credentials/role-name
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
LOWNetwork egressnet.metadata_ip · skills/security-review/references/ssrf.md:143
# Attacker: http://attacker.com/redirect -> http://169.254.169.254/
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
LOWNetwork egressnet.metadata_ip · skills/security-review/references/ssrf.md:215
if '169.254.169.254' in url or '169.254.170.2' in url:
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
LOWNetwork egressnet.metadata_ip · skills/security-review/references/ssrf.md:224
'metadata.google.internal',
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
LOWNetwork egressnet.raw_ip · skills/gha-security-review/references/runner-infrastructure.md:70
curl http://169.254.169.254/latest/meta-data/ # Cloud metadata (example of attack vector)
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWNetwork egressnet.raw_ip · skills/security-review/references/ssrf.md:19
http://169.254.169.254/latest/meta-data/iam/security-credentials/role-name
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWNetwork egressnet.raw_ip · skills/security-review/references/ssrf.md:43
http://192.168.1.1:22 # SSH
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWNetwork egressnet.raw_ip · skills/security-review/references/ssrf.md:44
http://192.168.1.1:3306 # MySQL
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWNetwork egressnet.raw_ip · skills/security-review/references/ssrf.md:45
http://192.168.1.1:6379 # Redis
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWObfuscation / stealthobf.decode_call · skills/skill-scanner/scripts/scan_skill.py:262
decoded = base64.b64decode(match.group()).decode("utf-8", errors="ignore")- Why
- No further detail recorded for this rule.
- Fix
- —
LOWPrompt injectionprompt.authority_framing · skills/gha-security-review/references/pwn-request.md:5
A "pwn request" occurs when a `pull_request_target` workflow checks out and executes code from a fork PR. The `pull_request_target` trigger runs with the **target repository's permissions and secrets*
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWPrompt injectionprompt.authority_framing · skills/skill-scanner/SKILL.md:155
- `Read Grep Glob Bash Write Edit WebFetch Task` — High risk, near-full access
- Why
- No further detail recorded for this rule.
- Fix
- —
Audit 0.4.1 · source sha 417b3e68b04d · 14 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishergetsentry GitHub organizationOwner of the repository this skill is read from
- Source foldergetsentry/skillsThe exact folder we audited
- LicenceApache-2.0As the repository states it
- Commit pinned for this verdict417b3e68b04dA new audit runs when the source changes
- Repository statusNot archivedLast push 8 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or…
--- name: agents-md description: Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain agent docs, set up CLAUDE.md, document repository agent conventions, or keep coding-agent instructions minimal and reference-backed. --- # Maintaining AGENTS.md Goal: concise, actionable agent instructions. Target under 60 lines; never exceed 100. ## Workflow 1. Inspect before writing: - package manager: lock files and manifests - commands: `package.json`, `Makefile`, task runners, CI workflows - docs/specs/policies: `README.md`, `CONTRIBUTING.md`, `docs/`, `specs/`, `policies/`, `SECURITY.md`, `.github/` - conventions: current code patterns, test layout, generated files, legacy areas to avoid 2. Choose scope: - root `AGENTS.md`: repo-wide defaults - nested `AGENTS.md`: only when a subtree has different commands or rules - closest instruction file wins; keep narrower files shorter than root files 3. Write the smallest useful file. 4. Verify exact paths and commands exist. ## File Setup - Create `AGENTS.md` at the repository root. - If a Claude-compatible entrypoint is required, symlink `CLAUDE.md` to `AGENTS.md`. - Do not maintain divergent `AGENTS.md` and `CLAUDE.md` copies. ## Default Sections Use only sections that add non-obvious value. ````markdown # Agent Instructions ## Package Manager - Use **pnpm**: `pnpm install` ## Commands | Task | Command | |------|---------| | Test file | `pnpm vitest run path/to/file.test.ts` | | Lint file | `pnpm eslint path/to/file.ts` | ## External References | Need | File | |------|------| | Setup | `CONTRIBUTING.md` | | Architecture | `docs/architecture.md` | | Security policy | `SECURITY.md` | ## Key Conventions - Generated files: update with `pnpm generate`; do not edit by hand. ## Commit Attribution AI commits MUST include: ``` Co-Authored-By: (the agent's name and attribution byline) ``` ```` ## Writing Rules - Use headings, bullets, and tables; avoid paragraphs. - Use repo-relative paths; avoid vague references like "see docs". - Reference existing docs/specs/policies instead of copying them. - List exact external files for setup, architecture, API specs, security, release, and policy docs when they exist. - Prefer file-scoped test/lint/typecheck commands; include full builds only when no narrower command exists. - Put commands in tables when there is more than one. - Keep one rule per bullet. - Keep rationale out unless it prevents a likely mistake. - Do not restate linter, formatter, or typechecker config. - Do not list installed skills or plugins. - Do not include generic quality slogans. ## External Reference Rules Good: ```markdown ## External References | Need | File | |------|------| | API contract | `docs/api.md` | | Release process | `docs/releasing.md` | ``` ## Anti-Patterns - welcome text, intros, conclusions, or pleasantries - long prose explaining why instructions matter - duplicated content from `README.md`, `CONTRIBUTING.md`, or policy docs - project-wide commands when file-scoped commands are available - nested `AGENTS.md` files that repeat root instructions
Excerpt, first 3,187 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 417b3e6
claude plugin install sentry-skills claude plugin install sentry-skills@sentry-skills npx skills add getsentry/skills git clone [email protected]:getsentry/skills.git ~/sentry-skills
git clone https://github.com/getsentry/skills git -C skills checkout 417b3e68b04d
Commands as the repository documents them: shown, never run by us. Our verdict covers commit 417b3e68b04d only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
| GitHub Copilot | Mentioned in its text, not tested | Skills for GitHub Copilot · About GitHub Copilot |
| Cursor | Mentioned in its text, not tested | Skills for Cursor · About Cursor |
Audit history
Every audit, every source change
- ✕BLOCK F 48 / 100
first audit · source
417b3e68b04d
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/getsentry/replay-ux-research/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
All design & front-end skills →getsentry/skills
Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune…
getsentry/skills
Create data-driven presentation slides using React, Vite, and Recharts with Sentry branding. Use when asked to "create a presentation", "build slides", "make a deck", "create a data presentation", "build a Sentry…
getsentry/skills
Append a GitHub issue link and its Linear ticket to the current PR's description. Use when asked to "link issue to pr", "fill in issue and linear in pr", "add issue refs to pr", or when given a GitHub issue URL and…
getsentry/skills
Create or refresh reviewer-facing PR titles and descriptions. Use when opening a PR, updating its title or body, or preparing branch changes for review.
getsentry/skills
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
getsentry/skills
Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find PRs I need to review", "show my review requests", "what needs my…
Add this badge to your README
[](https://modelsatlas.com/skills/getsentry/replay-ux-research/)
<a href="https://modelsatlas.com/skills/getsentry/replay-ux-research/"><img src="https://modelsatlas.com/skills/getsentry/replay-ux-research/badge.svg" alt="ModelsAtlas: BLOCK F"></a>
Questions about replay-ux-research
What does the replay-ux-research skill do?
Is replay-ux-research safe to install?
What can replay-ux-research access on my machine?
Which assistants does replay-ux-research work with?
How current is this page?
Sources
- github.com/getsentry/skills — the audited source at commit 417b3e68b04d and every finding aboveObserved · 14 Nov 2026
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.
- What does the replay-ux-research skill do?
- Is replay-ux-research safe to install?
- What can replay-ux-research access on my machine?