ClawAudit verdict
number-two-migration
The skill embeds what appears to be a real Moltbook API key ('moltbook_sk_4fM49PqzeqgI8jB5-qpV4x_CjiXAHHWW') in plaintext and references a truncated second API key, and it installs broad identity/memory/config files plus runs setup-api-keys.sh automatically, creating meaningful risk of credential exposure and unreviewed persistent agent reconfiguration.
⚠ 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.
Findings (5)
Possible hardcoded credential
config/skills/skills-auto-trigger.md · prose · downgraded · API_KEY="moltbook_sk_...
HTTP request to bare IP address — common in malicious payloads
config/memory/2026-03-06.md · prose · downgraded · http://127.0.0.1
Accesses shell history/config
install.sh · prose · downgraded · ~/.zshrc
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Opens WebSocket connection
config/memory/heartbeat-state-backup-2026-03-08.json · prose · downgraded · WebSocket
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
Is this flag fair?
Thanks — recorded.