Caveat verdict

agentguard

nano-agentguard

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

Security middleware skill managing agent credentials and permission scopes via the agentguard npm tool; all operations are documented CLI vault management actions.

⚠ 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.

18
security
80
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (7)

Pattern match critical

Possible hardcoded credential

docs/FEISHU-INTEGRATION.md · code · Password: 'your-password

Pattern match high

Accesses system credential store

TEST-REPORT.md · code · credential_store

Pattern match medium

Accesses sensitive environment variables

docs/FEISHU-INTEGRATION.md · code · process.env.AGENTGUARD_PASSWORD

Pattern match medium

References child_process — can spawn system processes

src/1password.js · prose · downgraded · child_process

Pattern match low

Node http/https module — low-level network access

src/feishu-notifier.js · prose · downgraded · require('https')

Pattern match low

References webhook/callback URL

src/feishu-notifier.js · prose · downgraded · webhookUrl

Pattern match low

Makes HTTP request to external URL

TEST-REPORT.md · code · fetch('https://

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). 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.

package_install

Is this flag fair?

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