Caveat verdict

mcp.json

ai-powered-literature-review-skills

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

The skill uses mcp_server_config capability and executionSinkDetected is true. However, the content seems to be focused on literature review tasks.

⚠ 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.

80
security
70
transparency
50
maintenance

Findings (1)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

mcp.json · config · http://127.0.0.1

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

No declared permissions — minimal attack surface.

mcp_server_config

Is this flag fair?

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