search-room

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill requires pulling the prior search's sessionId (and hotelId) from tool output and embedding it verbatim in CLI calls and responses (e.g., --session-id "" and JSON output), which forces the LLM to handle potentially sensitive session tokens in its generated output.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's "How to call" instructs running "npx @tvl-justin/travel-cli@latest", which at runtime fetches and executes a remote npm package (@tvl-justin/travel-cli@latest) that the skill depends on, so it is a runtime-executed external dependency that could control behavior.