ClawAudit verdict
semantic-memory
The skill appears to be a legitimate and transparent implementation of a Chinese semantic memory system, using capabilities like package_install in a clear and intended manner.
⚠ 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
package_install
Findings (2)
Pipe to python — executes piped content as Python code
README.md · prose · downgraded · | Python
Python os.environ.get — reads environment variable
scripts/import_memory.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/F). 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?
Thanks — recorded.