drug-discovery-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for their API key and then pass it directly as a command-line argument (scripts/search setup <api-key>), causing the secret to pass through the context and output in an insecure manner.

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

• Third-party content exposure detected (low risk: 0.10). The agent performs a search query across drug discovery databases using the Valyu API, ingesting search results containing third-party compound, target, and drug data.