Caveat verdict

bookmark-intelligence

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill sends data to external services (e.g., Telegram, API calls) which may be beyond its need.

⚠ 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.

60
security
60
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (4)

Pattern match high

Possible hardcoded credential

monitor.js · prose · downgraded · TOKEN=')) { credentials.auth_token = line.substring(

Pattern match medium

References child_process — can spawn system processes

analyzer.js · prose · downgraded · child_process

Pattern match low

Accesses sensitive environment variables

monitor.js · prose · downgraded · process.env.AUTH_TOKEN

Pattern match low

Popular HTTP library — network access

scripts/setup.js · prose · downgraded · got

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