Caveat verdict

mcp.json

aihotel

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

Hardcoded credentials in config AND network transport

MCP-based hotel search skill that passes user-supplied query parameters to the AIGoHotel MCP server tools; no credential exfiltration or suspicious behavior, credential in config is normal MCP pattern.

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.

60
security
60
transparency
50
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Hardcoded credentials in config AND network transport — credentials may be exposed to a remote server

LLM02 · LLM03 · ASI03 · ASI04

Permissions & capabilities

No declared permissions — minimal attack surface.

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