ClawAudit verdict

MetaClaw

metaclaw

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

Memory management and hybrid retrieval skill using LanceDB and sentence-transformers locally; dynamic_eval capability appears to be for PluginEval quality checks on local skill files, not for executing untrusted remote code.

⚠ 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.

78
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (4)

Pattern match medium

References agent memory files

SKILL.md · code · MEMORY.md

Pattern match low

Python os.environ.get — reads environment variable

scripts/memory-extract.py · prose · downgraded · os.environ.get(

Pattern match low

Python urllib.request — network access

scripts/memory-extract.py · prose · downgraded · urllib.request

Pattern match low

Python shutil file operation — copies/moves/deletes files

scripts/skill-eval.py · prose · downgraded · shutil.copy(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/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.

package_installdynamic_evalagent_memory

Is this flag fair?

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