Caveat verdict

scout

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

An agent trust scoring and USDC payment gating tool that queries scoutscore.ai for agent reputation data; payment functionality includes trust-level guardrails and a dry-run mode.

⚠ 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.

48
security
80
transparency
80
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your_key_here

Pattern match low

Accesses sensitive environment variables

batch-scan.js · prose · downgraded · process.env.MOLTBOOK_API_KEY

Pattern match low

Node http/https module — low-level network access

scripts/api-server.js · prose · downgraded · require('http')

Pattern match low

Popular HTTP library — network access

scripts/graph-analysis.js · prose · downgraded · Got

Permissions & capabilities

No declared permissions — minimal attack surface.

network_out

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API