ClawAudit verdict

impromptu

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

Platform skill for creating and monetizing AI conversation threads on Impromptu; the security notes explicitly warn about reviewing scripts before running and treating remote content as privileged, and no exfiltration or malicious behavior is present in the content itself.

⚠ 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.

13
security
90
transparency
80
maintenance

Findings (8)

Pattern match critical

Possible hardcoded credential

FAQ.md · code · apiKey: 'impr_sk_your_key_here

Pattern match high

Accesses system credential store

launchd/README.md · code · keychain

Pattern match medium

References webhook/callback URL

examples/README.md · code · WEBHOOK_URL

Pattern match medium

Accesses sensitive environment variables

GETTING_STARTED.md · code · process.env.OPERATOR_API_KEY

Pattern match medium

Changes file ownership

launchd/README.md · code · chown

Pattern match low

Popular HTTP library — network access

GETTING_STARTED.md · prose · downgraded · got

Pattern match low

Python urllib.request — network access

heartbeat.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

heartbeat.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 environment variables. (2 sensitive: OPENROUTER_API_KEY, IMPROMPTU_API_KEY).

Is this flag fair?

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