ClawAudit verdict
minimax-monitor
The skill uses capabilities like network_in and credential_access for legitimate purposes, loading local credentials on demand and making outbound API calls for quota monitoring and rate testing.
⚠ 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
credential_access
Findings (4)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
Writes to SKILL.md — self-modifying skill
SKILL.md · prose · downgraded · SKILL.md` frontmatter `permissions:` lists `write
References child_process — can spawn system processes
mmx-monitor-server.js · prose · downgraded · child_process
Node http/https module — low-level network access
mmx-monitor-server.js · prose · downgraded · require('http')
Permissions & capabilities
No declared permissions — minimal attack surface.
network_incredential_access Is this flag fair?
Thanks — recorded.