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

Agent skill · Audited from source

continuity-ledger

skill · parcadei/continuous-claude-v3MIT licenceAudited 13 Nov 2026 · source 79ffdab59d4c

★ 3,949pushed 290 days agoversion 3.0
✕BLOCKGrade F · 36/100 · 25 findings · 79ffdab
3,949repo stars · whole parcadei/continuous-claude-v3

Is it safe? No — BLOCK, grade F (36/100). We read this skill's source at commit 79ffdab59d4c and observed filesystem, network and shell access and a hard-coded secret (see the findings). The audit raised 25 findings, 12 critical or high. What it does: Agent Context Isolation

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “continuity-ledger (parcadei/continuous-claude-v3)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/parcadei/continuity-ledger

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 12 critical or high findings, starting with “Code injection” in opc/docker/sandbox_runner.py:174. Do not install it without reading them.

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score36/100✕BLOCK F
0 critical12 high9 medium18 low0 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

  • FilesystemDeclared1 observation
  • NetworkDeclared16 observations
  • ShellDeclared10 observations
  • DependenciesNot pinnedSome versions float
  • SecretsFoundSee the findings; values are never shown

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN4
L1 Static sourceSecrets, path traversal, supply chain, hidden codeFAIL18
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL3
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 · opc/docker/sandbox_runner.py:174
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
exec(code, restricted_globals, local_vars)
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · opc/scripts/cc_math/math_base.py:526
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
return eval(func_str, namespace, {})
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · opc/scripts/cc_math/math_base.py:536
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
return eval(lambda_str, namespace, {})
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · opc/scripts/cc_math/pint_compute.py:284
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
result = eval(safe_expr, {"__builtins__": {}}, safe_namespace)
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · opc/scripts/cc_math/scipy_compute.py:166
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
return np.array([eval(eq, namespace) for eq in equations])
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHNetwork egressnet.tls_off · opc/scripts/core/db/embedding_service.py:457
F-04 Network egressCWE-200 · CWE-319Layer L1
self._client = httpx.AsyncClient(timeout=30.0, verify=False)
Why
certificate verification is disabled
Fix
leave verification on
HIGHHard-coded secretssecret.db_uri · .claude/hooks/dist/shared/db-utils-pg.js:28
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1
'…';
Why
No further detail recorded for this rule.
Fix
—
HIGHHard-coded secretssecret.db_uri · .claude/hooks/src/shared/db-utils-pg.ts:37
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1
'…';
Why
No further detail recorded for this rule.
Fix
—
HIGHHard-coded secretssecret.db_uri · opc/pyproject.toml:164
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1
runner = "…"
Why
No further detail recorded for this rule.
Fix
—
HIGHHard-coded secretssecret.db_uri · opc/scripts/claude_spawn.py:199
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1
"…"
Why
No further detail recorded for this rule.
Fix
—
HIGHPrompt injectionprompt.credential_read · .claude/skills/hook-developer/SKILL.md:205
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
**Purpose:** Initialize session, load context, set environment variables.
Why
asks the agent to read credentials
Fix
—
HIGHPrompt injectionprompt.override · README.md:1120
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
**Windows users:** Use PowerShell (as Administrator or with Developer Mode enabled):
Why
asks the agent to drop prior instructions or safety
Fix
remove the instruction
MEDIUMCode injectioncode.dynamic_import · opc/scripts/setup/math_features.py:35
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
__import__(pkg)
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · .claude/hooks/dist/compiler-in-the-loop.js:14
F-04 Network egressCWE-200 · CWE-319Layer L1
const LMSTUDIO_BASE_URL = process.env.LMSTUDIO_BASE_URL || 'http://127.0.0.1:1234';
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · .claude/hooks/dist/compiler-in-the-loop.mjs:6
F-04 Network egressCWE-200 · CWE-319Layer L1
var LMSTUDIO_BASE_URL = process.env.LMSTUDIO_BASE_URL || "http://127.0.0.1:1234";
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · .claude/hooks/src/compiler-in-the-loop.ts:17
F-04 Network egressCWE-200 · CWE-319Layer L1
const LMSTUDIO_BASE_URL = process.env.LMSTUDIO_BASE_URL || 'http://127.0.0.1:1234';
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · opc/scripts/loogle_search.py:24
F-04 Network egressCWE-200 · CWE-319Layer L1
SERVER_URL = "http://127.0.0.1:8340"
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · opc/scripts/loogle_server.py:197
F-04 Network egressCWE-200 · CWE-319Layer L1
print(f"Loogle server listening on http://127.0.0.1:{PORT}")
Why
No further detail recorded for this rule.
Fix
—
MEDIUMHard-coded secretssecret.db_uri · .claude/rules/cross-terminal-db.md:7
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1
DATA…://…@localhost:5432…
Why
No further detail recorded for this rule.
Fix
—
MEDIUMSupply chainprompt.pipe_to_shell · .claude/skills/prove/SKILL.md:25
F-08 Supply chainCWE-829 · CWE-1357Layer L2
curl https://raw.githubusercontent.com/leanprover/elan/master/elan-init.sh -sSf | sh
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenanceinv.hidden_file · .coderabbit.yaml
F-13 Inventory / provenanceCWE-1104Layer L0
.coderabbit.yaml
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · .tldrignore
F-13 Inventory / provenanceCWE-1104Layer L0
.tldrignore
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · opc/.tldrignore
F-13 Inventory / provenanceCWE-1104Layer L0
.tldrignore
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInsecure cryptocrypto.weak_hash · .claude/hooks/dist/__tests__/daemon-client.test.js:29
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
const hash = crypto.createHash('md5').update(projectDir).digest('hex').substring(0, 8);
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 79ffdab59d4c · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherparcadei GitHub userOwner of the repository this skill is read from
  • Source folderparcadei/continuous-claude-v3The exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict79ffdab59d4cA new audit runs when the source changes
  • Repository statusNot archivedLast push 290 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Agent Context Isolation

---
name: agent-context-isolation
description: Agent Context Isolation
user-invocable: false
---

# Agent Context Isolation

Prevent agent output from polluting the main context window.

## Rules

### 1. Use Background Agents with File-Based Coordination
```
# RIGHT - background agent writes to file, main reads file
Task(subagent_type="...", run_in_background=true, prompt="... Output to: /path/to/file.md")

# WRONG - foreground agent dumps full transcript into main context
Task(subagent_type="...", run_in_background=false)
```

Background agents with `run_in_background=true` isolate their context. Have them write results to files in `.claude/cache/agents/<agent-type>/`.

### 2. Never Use TaskOutput to Retrieve Results
```
# WRONG - dumps entire transcript (70k+ tokens) into context
TaskOutput(task_id="<id>")
TaskOutput(task_id="<id>", block=true)

# RIGHT - check expected output files
Bash("ls -la .claude/cache/agents/<agent-type>/")
Bash("bun test")  # verify with tests
```

TaskOutput returns the full agent transcript. Always use file-based coordination instead.

### 3. Monitor Agent Progress via System Reminders
```
# System reminders come automatically:
# "Agent a42a16e progress: 6 new tools used, 88914 new tokens"

# To detect completion:
# - Watch for progress reminders to stop arriving
# - Poll for expected output files: find .claude/cache/agents -name "*.md" -mmin -5
# - Check task output file size growth: wc -c /tmp/claude/.../tasks/<id>.output
```

**Stuck agent detection:**
1. Progress reminders stop arriving
2. Task output file size stops growing
3. Expected output file not created after reasonable time

### 4. Verify with Tests, Not Output
After agent work:
1. Run the test suite directly: `bun test`
2. Report pass/fail counts
3. Only investigate failures if tests fail

### 5. File-Based Agent Pipeline Pattern
```
Research agent → .claude/cache/agents/oracle/output.md
                          ↓
Plan agent → .claude/cache/agents/plan-agent/output.md (reads research)
                          ↓
Validate agent → .claude/cache/agents/validate-agent/output.md (reads plan)
                          ↓
Implement agent → src/module.ts (reads validated plan)
```

Each agent reads the previous agent's file output, not TaskOutput.

## Why This Matters

Agent context isolation preserves the main conversation's context budget. Reading agent outputs via TaskOutput floods context, causing:
- Mid-conversation compaction
- Lost context about user's original request
- Repeated explanations needed

## Source
- Session where TaskOutput flooded 70k+ tokens into main context
- Session 2026-01-01: Successfully used background agents with file-based coordination for SDK Phase 3

Excerpt, first 2,714 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 79ffdab

uv run python -m runtime.harness scripts/perplexity_ask.py \
pip install agentica
uv add agentica
uv run pytest tests/unit/ -v --tb=short -q
uv run pytest tests/unit/ --cov=src --cov-report=term-missing
uv run pytest tests/integration/ -v --tb=short

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 79ffdab59d4c 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
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“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 36 / 100

    first audit · source 79ffdab59d4c

README badge

For maintainers · shows the latest audit

ModelsAtlas: BLOCK FMODELSATLASBLOCK · F
[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/parcadei/continuity-ledger/badge.svg)](https://modelsatlas.com/skills/parcadei/continuity-ledger/)

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

Similar skills

Add this badge to your README

[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/parcadei/continuity-ledger/badge.svg)](https://modelsatlas.com/skills/parcadei/continuity-ledger/)

Questions about continuity-ledger

What does the continuity-ledger skill do?
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Is continuity-ledger safe to install?
No — not without reading the findings first. The audit graded it F (36/100) and found 12 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What can continuity-ledger 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 continuity-ledger work with?
Its documentation mentions claude-code, copilot and cursor. 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 (79ffdab59d4c), 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.