pubmed-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to ask the user for their API key and then pass it directly as a command-line argument to a setup script (scripts/search setup <api-key>), causing the secret to pass through the LLM context and execution logs.

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

• Third-party content exposure detected (low risk: 0.10). The workflow actively searches and fetches biomedical literature from PubMed via the Valyu search API, making outsider-authored content (articles and papers) low-risk indirect prompt injection input.