ClawAudit verdict
clawlock
ClawLock is a security scanner that installs via pip and runs local-first analysis; the executionSinkDetected flag is explained by the documented clawlock CLI commands, and the privacy section explicitly states what minimal data is sent (product names/versions, no credentials, no file contents).
⚠ 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.
Permission integrity
package_install
agent_memory
Findings (6)
Writes to SKILL.md — self-modifying skill
SKILL_EN.md · prose · downgraded · SKILL.md](SKILL.md). Output language follows the user's language: if the user wr
References sudo — requests elevated privileges
SKILL.md · prose · downgraded · sudo
Sets world-executable permissions
SKILL.md · prose · downgraded · chmod 777
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
importlib.import_module — dynamic module loading
SKILL.md · prose · downgraded · importlib.import_module(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C). 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.
package_installnetwork_inagent_memory Is this flag fair?
Thanks — recorded.