clinical-trials-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly tells the agent to ask the user for their Valyu API key and then run commands like scripts/search setup <api-key> and shows examples embedding API keys in code/CLI, which requires the LLM to include the secret verbatim in its outputs.

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

• Third-party content exposure detected (high risk: 0.70). The skill calls the Valyu API from scripts/search.mjs and SKILL.md describes returning full trial information (results[].content and results[].url) pulled from public ClinicalTrials.gov via Valyu, so the agent ingests and acts on untrusted third‑party web content as part of its workflow.