ClawAudit verdict

django-claw

django-claw-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Django management command dispatcher that runs local scripts for migrate, showmigrations, ORM queries, and other standard Django operations; explicit rules against destructive commands without confirmation.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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.

30
security
90
transparency
70
maintenance

Findings (4)

Pattern match high

Pipe to bash — executes piped content as shell commands

SKILL.md · prose · downgraded · | bash

Pattern match high

Pipe to python — executes piped content as Python code

scripts/load-config.sh · prose · downgraded · | PYTHON

Pattern match high

Dynamic __import__('os') — Python OS command execution

scripts/readonly.sh · prose · downgraded · __import__('os')

Pattern match medium

Accesses OpenClaw config/secrets directly

scripts/setup.sh · prose · downgraded · ~/.openclaw/openclaw.json

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 system binaries.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API