Writes, tests, registers and debugs Claude Code hooks (PreToolUse, PostToolUse, SessionStart, Stop) that turn a rule the model keeps breaking into a hard gate. Use when the user wants to block or intercept a tool call, add a guard rail, fix a misfiring hook, or says 拦截 / 守卫 / 钩子, including "make it stop doing X".
- 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 · 36
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:37 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:426 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:433 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:503 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1314 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1363 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1371 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:116 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:139 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:236 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:250 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:355 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:374 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:394 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:455 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1033 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1067 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1087 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1362 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1372 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:181 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:235 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:315 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:914 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1222 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1316 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1339 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1351 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1364 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:1365 · skillspector:AE1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:373 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
references/hook_pitfalls.md:2104 · skillspector:AS1
- high
Tool Misuse: Chaining Abuse
references/hook_patterns.md:705 · skillspector:TM2
- high
Tool Misuse: Tool Parameter Abuse
references/hook_pitfalls.md:737 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
references/hook_pitfalls.md:774 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
references/hook_pitfalls.md:780 · skillspector:TM1
medium · 14
- medium
Trigger Abuse: Shadow Command Trigger
SKILL.md:1 · skillspector:TR2
- medium
Privilege Escalation: Sudo/Root Execution
SKILL.md:239 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
SKILL.md:241 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
references/hook_patterns.md:235 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
references/hook_patterns.md:254 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
references/hook_patterns.md:409 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
references/hook_patterns.md:490 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
scripts/test_hook.sh:79 · skillspector:PE2
- medium
Excessive Agency: Autonomous Decision Making
SKILL.md:280 · skillspector:EA2
- medium
Rogue Agent: Session Persistence
SKILL.md:323 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:895 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:895 · skillspector:RA2
- medium
Excessive Agency: Autonomous Decision Making
SKILL.md:1144 · skillspector:EA2
- medium
Rogue Agent: Session Persistence
references/hook_patterns.md:152 · skillspector:RA2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-162 added, 2 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
8 files, 438 KB in total. Names only; open them on GitHub.
- SKILL.md
- references/effect-and-cost-audit.md
- references/hook_patterns.md
- references/hook_pitfalls.md
- references/recovery-failure-triage.md
- references/shared-engine-lifecycle.md
- scripts/test_hook.group-name-guard.sh
- scripts/test_hook.sh
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
claude-switch-models-setupdaymadeIsolates profiles for multi-provider setup and switching models in separate terminal windows (Kimi, MiniMax, DeepSeek, GLM, StepFun,… High riskEngineeringAI & agents1.5k
prior-work-retrievaldaymadeOnly for explicit prior-work/reuse/history requests, not status checks. Finds and verifies existing work before new production when reuse… High riskEngineeringAI & agents1.5k
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