ClawAudit verdict

swarma

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

Growth experiment automation tool that runs A/B test cycles via OpenRouter API using the user's own API key; all writes are to local files and no credential exfiltration is present.

⚠ 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.

58
security
80
transparency
90
maintenance

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (1)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY: "sk-or-...

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/C). 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_installnetwork_infile_write

Is this flag fair?

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