ClawAudit verdict

openmem

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill reads session transcripts and stores compressed memories in a local database. While it does not exfiltrate data, the handling of sensitive information requires scrutiny.

⚠ 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
90
transparency
70
maintenance

Findings (7)

Pattern match high

Pipe to python — executes piped content as Python code

hooks/openclaw/HOOK.md · prose · downgraded · | Python

Pattern match medium

Instructs covert action — may act without user awareness

hooks/openclaw/HOOK.md · prose · downgraded · silently

Pattern match medium

subprocess execution — runs system commands from Python

scripts/auto_compress.py · prose · downgraded · subprocess.run(

Pattern match medium

Social engineering — falsely claims user authorization

scripts/auto_compress.py · prose · downgraded · the user has configured

Pattern match low

References agent memory files

SKILL.md · prose · downgraded · MEMORY.md

Pattern match low

Python os.environ.get — reads environment variable

scripts/auto_compress.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

scripts/setup.py · prose · downgraded · got

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

Requires 1 system binary.

Is this flag fair?

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