ClawAudit verdict

predicate-snapshot

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

DOM snapshot pruning tool that optionally sends page snapshots to predicate.systems for ML ranking; the API key is optional, the service is documented, and the behavior matches the stated token-reduction purpose.

⚠ 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.

18
security
50
transparency
80
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (4)

Pattern match critical

Possible hardcoded credential

docs/INSTALL_AND_TEST.md · code · API_KEY="sk-your-api-key-here

Pattern match high

Accesses shell history/config

docs/INSTALL_AND_TEST.md · code · ~/.zshrc

Pattern match medium

Dynamic import() — loads module at runtime

demo/compare.ts · prose · downgraded · import('

Pattern match low

Accesses sensitive environment variables

demo/compare.ts · prose · downgraded · process.env.PREDICATE_API_KEY

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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_installcredential_access

Is this flag fair?

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