Caveat verdict

MDClaw 多模态

mdclaw-openclaw

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Multimodal AI gateway using API key from environment variables to call a documented backend endpoint; credential_access limited to reading MDCLAW_API_KEY consistent with stated purpose.

⚠ 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.

50
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="你的API Key

Pattern match low

Python os.getenv — reads environment variable

examples/basic_usage.py · prose · downgraded · os.getenv(

Pattern match low

Python os.environ.get — reads environment variable

examples/test_connection.py · prose · downgraded · os.environ.get(

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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