ClawAudit verdict
moltmarkets-agent
The skill uses credential access to set up a MoltMarkets agent, but it is for its legitimate purpose and seems secure.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
Instructs covert action โ may act without user awareness
references/cron-definitions.md ยท code ยท SILENTLY
Node http/https module โ low-level network access
scripts/setup.js ยท prose ยท downgraded ยท require('https')
Permissions & capabilities
No declared permissions โ minimal attack surface.
credential_access Is this flag fair?
Thanks โ recorded.