Caveat verdict
auto-skill-extractor
Writes files AND executes processes
A local skill management tool that monitors subagent completions, scores complexity, and auto-promotes reusable skill drafts; all file operations are local skill directory management with no unexpected network access.
Automated static analysis — not a human review. Caveat 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 Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Writes files AND executes processes — may drop and execute malicious scripts
LLM05 · LLM06 · ASI05
Both reads and writes files — verify scope is limited to intended directories
LLM06 · ASI02
Findings (3)
subprocess execution — runs system commands from Python
SKILL.md · code · subprocess.run(
Writes to SKILL.md — self-modifying skill
auto-skill-trigger.py · prose · downgraded · SKILL.md").write
Python os.environ.get — reads environment variable
scripts/auto-skill-trigger.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
file_readfile_writeprocess_exec Thanks — recorded.