ClawAudit verdict
hook-authoring
nm-abstract-hook-authoring
Accesses agent memory AND writes files
Educational documentation for writing Claude Code hooks; file read/write capabilities are used to create hook configuration files as expected for an authoring guide.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses agent memory AND writes files — may modify agent behavior persistently
LLM01 · LLM06 · ASI01 · ASI06
Both reads and writes files — verify scope is limited to intended directories
LLM06 · ASI02
Permission integrity
file_read+write
agent_memory
Findings (5)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
Python aiohttp session — async network access
modules/performance-guidelines.md · code · aiohttp.ClientSession
Python os.getenv — reads environment variable
modules/sdk-callbacks.md · code · os.getenv(
References agent configuration files
modules/hook-types.md · prose · downgraded · CLAUDE.md
Permissions & capabilities
No declared permissions — minimal attack surface.
file_writeagent_memoryfile_read Thanks — recorded.