ClawAudit verdict

auto-midjourney

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

Submits prompts to the user's own authenticated Midjourney Alpha session using user-provided credentials stored in environment variables; all API calls are to the user's own account with explicit safety guardrails and conservative throttling.

⚠ 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
90
transparency
80
maintenance

Findings (8)

Pattern match medium

subprocess execution — runs system commands from Python

scripts/mj_alpha.py · prose · downgraded · subprocess.run(

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/mj_browser.py · prose · downgraded · http://127.0.0.1

Pattern match medium

Base64 decode (atob) — may hide malicious payloads

scripts/mj_browser.py · prose · downgraded · atob(

Pattern match low

Python urllib.request — network access

scripts/mj_alpha.py · prose · downgraded · urllib.request

Pattern match low

Python os.getenv — reads environment variable

scripts/mj_alpha.py · prose · downgraded · os.getenv(

Pattern match low

Popular HTTP library — network access

scripts/mj_alpha.py · prose · downgraded · got

Pattern match low

Base64 encode (btoa) — may obfuscate data exfiltration

scripts/mj_browser.py · prose · downgraded · btoa(

Pattern match low

String.fromCharCode — can build strings to evade detection

scripts/mj_browser.py · prose · downgraded · String.fromCharCode

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.

network_in

Is this flag fair?

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