Caveat verdict

twitter-cli

twitter-command

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

The skill explicitly instructs agents to ask users to paste their complete Twitter browser cookie string and then parses auth_token and ct0 from it, harvesting live session credentials even if transparently disclosed.

⚠ 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.

25
security
100
transparency
90
maintenance

Findings (6)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="<auth_token from browser>

Pattern match high

HTTP request to bare IP address — common in malicious payloads

README.md · code · http://127.0.0.1

Pattern match medium

Accesses system credential store

README.md · prose · downgraded · Keychain

Pattern match medium

subprocess execution — runs system commands from Python

twitter_cli/auth.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

twitter_cli/auth.py · prose · downgraded · os.environ.get(

Pattern match low

Python os.getenv — reads environment variable

twitter_cli/output.py · prose · downgraded · os.getenv(

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.

Is this flag fair?

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