ClawAudit verdict
memory-garden
The skill uses network_out and network_in capabilities to learn and validate knowledge patterns.
⚠ 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
network_out
Findings (4)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
References child_process — can spawn system processes
daemon-manager.ts · prose · downgraded · child_process
Uses spawn() — can execute external programs
daemon-manager.ts · prose · downgraded · spawn(
Base64 encoding/decoding
identity.ts · prose · downgraded · Base64-encode
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.
network_outnetwork_in Is this flag fair?
Thanks — recorded.