drugbank-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to ask the user for their Valyu API key and then run a command that embeds that key as a command-line argument (scripts/search setup ), which requires the LLM to handle and output the secret verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow sends the user-provided free-text “query” to Valyu’s /search endpoint via scripts/search.mjs (fetch(.../search) with body: { query: query, ... }), so an outsider can inject arbitrary text that the system transmits for retrieval/search.