Caveat verdict
openclaw-multi-brain
Multi-LLM perspective skill that calls Kimi K2.5 and GPT Codex in parallel to inject perspectives into context; the external API calls are transparent, user-triggered via keyword, and serve the stated cognitive diversity purpose.
⚠ 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
credential_access
package_install
Findings (7)
Recursive delete from root or home — destructive command
QUICKSTART.md · code · rm -rf ~
References sudo — requests elevated privileges
QUICKSTART.md · code · sudo
Accesses system credential store
BUILD-SUMMARY.md · prose · downgraded · keychain
Reads files from sensitive system paths
daemon/dual-brain-watcher.js · prose · downgraded · readFileSync('/Users
References child_process — can spawn system processes
src/cli.js · prose · downgraded · child_process
References agent memory files
BUILD-SUMMARY.md · prose · downgraded · MEMORY.md
Node http/https module — low-level network access
daemon/dual-brain-watcher.js · prose · downgraded · require('https')
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
No declared permissions — minimal attack surface.
credential_accesspackage_install Is this flag fair?
Thanks — recorded.