ClawAudit verdict
mhc-algorithm
mhc-layer-impl-mhc-algorithm
88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose
The skill is used to implement the mHC algorithm for stabilizing deep network training, and its capabilities are used legitimately and transparently for its stated purpose.
⚠ 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.
95
security
70
transparency
70
maintenance
Permission integrity
Installs packages at runtime — transitive dependencies are not auditable
package_install
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.