drug-discovery-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 shell command embedding that key as a command-line argument (scripts/search setup ), which requires the LLM to output the secret verbatim.

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow reads only user-provided natural-language query and sends it to Valyu’s /search API, but it does not ingest any outsider-authored free text feed/queue item selected without first fetching via the user’s query; it returns first-party database content (via Valyu) rather than LLM-ingesting arbitrary submitted text from an external authoring path.