ClawAudit verdict
memory-palace
The skill requires installation of a package (memory-palace), which could potentially be used for malicious purposes.
⚠ 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 (5)
Uses exec() — may execute shell commands
bin/memory-palace.js · prose · downgraded · exec(
References child_process — can spawn system processes
src/background/vector-search.ts · prose · downgraded · child_process
Uses spawn() — can execute external programs
src/background/vector-search.ts · prose · downgraded · spawn(
Instructs covert action — may act without user awareness
src/manager.ts · prose · downgraded · Silently
Python os.environ.get — reads environment variable
scripts/vector-service.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
package_install Is this flag fair?
Thanks — recorded.