Only for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse is plausible. Use when the user explicitly references earlier work, existing code, history, or prior decisions, or says 以前做过, 已有代码, 别重复造轮子. Not for current tests, files, bug fixes, or mechanical verification. Produces a reuse/adapt/reject receipt; zero hits never prove absence.
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 50 findings, highest severity high.
- Highest severity
- high
- Findings
- 50
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked yesterday
Result
High risk Waxell rates it high risk: 50 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (50)
high · 11
- high
Tool Misuse: Chaining Abuse
scripts/prior_work_hook.py:927 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/test_prior_work_hook.py:1096 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/test_prior_work_hook.py:1100 · skillspector:TM2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_current_execution.py:290 · skillspector:E2
- high
Tool Misuse: Tool Parameter Abuse
tests/test_prior_work_hook.py:777 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/test_prior_work_hook.py:777 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/test_prior_work_hook.py:777 · skillspector:TM1
- high
Data Exfiltration: Env Variable Harvesting
tests/test_prior_work_hook.py:1738 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_prior_work_hook.py:1755 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_prior_work_hook.py:1779 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_source_freshness.py:28 · skillspector:E2
medium · 39
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Agent Snooping: Skill Enumeration
SKILL.md:215 · skillspector:AS3
- medium
Agent Snooping: Skill Enumeration
SKILL.md:216 · skillspector:AS3
- medium
Dangerous Code Execution: subprocess module call
scripts/prior_work.py:265 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'root' from pathlib.Path.read_text (line 1115, file read) → subprocess.run (code execution)
scripts/prior_work.py:265 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/prior_work.py:363 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'cwd' from os.environ.get (line 349, credential/environment) → subprocess.run (code execution)
scripts/prior_work.py:363 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/prior_work.py:386 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'repo' from pathlib.Path.read_text (line 481, file read) → subprocess.run (code execution)
scripts/prior_work.py:386 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/prior_work.py:404 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'repo' from os.environ.get (line 422, credential/environment) → subprocess.run (code execution)
scripts/prior_work.py:404 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/prior_work.py:577 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/prior_work.py:657 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/prior_work.py:800 · skillspector:AST4
- medium
Output Handling: Unbounded Output
scripts/verify_artifact.py:51 · skillspector:OH3
- medium
Dangerous Code Execution: subprocess module call
tests/test_current_execution.py:63 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_current_execution.py:293 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work.py:410 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work.py:411 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work.py:415 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work.py:419 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work.py:422 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work.py:438 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work.py:441 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'payload' from pathlib.Path.read_text (line 631, file read) → pathlib.Path.write_text (file wri
tests/test_prior_work.py:633 · skillspector:TT2
- medium
Rogue Agent: Session Persistence
tests/test_prior_work_hook.py:121 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
tests/test_prior_work_hook.py:121 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
tests/test_prior_work_hook.py:1388 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
tests/test_prior_work_hook.py:1388 · skillspector:RA2
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work_hook.py:1733 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work_hook.py:1761 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'env' from os.environ.get (line 1755, credential/environment) → subprocess.run (code execution)
tests/test_prior_work_hook.py:1761 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
tests/test_prior_work_hook.py:1774 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_source_freshness.py:43 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_source_freshness.py:51 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_source_freshness.py:196 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'payload' from pathlib.Path.read_text (line 297, file read) → pathlib.Path.write_text (file wri
tests/test_source_freshness.py:303 · skillspector:TT2
- medium
Data Flow: Tainted flow: 'payload' from pathlib.Path.read_text (line 315, file read) → pathlib.Path.write_text (file wri
tests/test_source_freshness.py:317 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
tests/test_source_freshness.py:328 · skillspector:AST4
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-161 added, 6 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
17 files, 358 KB in total. Names only; open them on GitHub.
- SKILL.md
- evals/evals.json
- references/source-manifest.md
- references/visual-result-reuse.md
- scripts/prior-work-retrieval.sh
- scripts/prior_work.py
- scripts/prior_work_hook.py
- scripts/surface_version.py
- scripts/verify_artifact.py
- tests/fixtures/manifest.json
- tests/test_current_execution.py
- tests/test_prior_work.py
- tests/test_prior_work_hook.py
- tests/test_scope_path_cost.py
- tests/test_source_freshness.py
- tests/test_surface_version.py
- tests/test_verify_artifact.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
local-codexdaymadeLaunches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate… High riskEngineeringAI & agents1.5k
macos-cleanerdaymadeDiagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign… High riskEngineeringData & analytics1.5k
macos-watchdogdaymadeDesigns and audits macOS launchd watchdogs: LaunchAgent/LaunchDaemon setup, plist edits, scheduled self-healing, repeated notifications,… High riskEngineeringDesign1.5k
skill-governancedaymadeGoverns the Claude Code/Codex Skill surface: reconciles source/install/catalog-visibility drift without losing cold capability. Use when… High riskEngineeringAI & agents1.5k