ClawAudit verdict

agent-mem

18
🔴 Dangerous
High-risk patterns flagged for review — automated deep scan, not behaviorally verified.

The skill executes a pip install command which could be risky if the package source is not trusted.

⚠ 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.

43
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match high

Uses eval() — can execute arbitrary code

engine_v2.py · prose · downgraded · eval(

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

dispatch.py · prose · downgraded · http://127.0.0.1

Pattern match medium

Uses exec() — may execute shell commands

engine_v2.py · prose · downgraded · exec(

Pattern match medium

subprocess execution — runs system commands from Python

memory_recall.py · prose · downgraded · subprocess.run(

Pattern match low

References agent memory files

memory_recall.py · prose · downgraded · MEMORY.md

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.

package_install

Is this flag fair?

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