Caveat verdict
agent-registry
The skill provides lazy-loading for Claude Code agents, reducing context window usage without malicious behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
agent_memory
Findings (4)
Accesses sensitive system files
tests/registry.test.js · prose · downgraded · /etc/passwd
Instructs covert action — may act without user awareness
CLAUDE.md · prose · downgraded · silently
References child_process — can spawn system processes
tests/cli.test.js · prose · downgraded · child_process
Uses spawn() — can execute external programs
tests/cli.test.js · prose · downgraded · spawn(
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
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.