ClawAudit verdict

agentmemo

agentmemo-karl

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

This skill runs a localhost-only (127.0.0.1:8790) semantic memory server with mandatory API key auth, RBAC, and explicit warnings against internet exposure; behavior is consistent with its stated purpose as a local memory mesh for agent sessions.

⚠ 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.

23
security
20
transparency
70
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · api_key="your-secret-key

Pattern match medium

Opens WebSocket connection

SKILL.md · frontmatter · WebSocket

Pattern match medium

Instructs covert action — may act without user awareness

benchmark/ACCEPTANCE_CHECKLIST.md · prose · downgraded · silently

Pattern match low

Python urllib.request — network access

benchmark.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

benchmark/agentvault_eval.py · prose · downgraded · os.environ.get(

Pattern match low

Blob URL — may embed executable content

embeddings.py · prose · downgraded · blob:

Permissions & capabilities

No declared permissions — minimal attack surface.

package_installnetwork_incredential_accessnetwork_out

Is this flag fair?

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