drug-labels-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly tells the agent to ask the user for their Valyu API key and then run a command embedding that key verbatim (scripts/search setup ), requiring the LLM to handle and output the secret directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill calls Valyu’s /search API and returns data.results including content (FDA label text) into the agent context; this is outsider-authored free text fetched at runtime from an external service (public FDA drug labels), not authored by the operating user.