literature-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask the user for their Valyu API key and then run a shell command embedding that key (scripts/search setup ) and shows examples that place API keys directly in code, which requires the LLM to handle and output secret values verbatim and therefore is high-risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls the Valyu API to search/public literature sources (PubMed, arXiv, bioRxiv, medRxiv) and returns full article "content" (see SKILL.md and scripts/search.mjs where included_sources are set and results[].content is returned), meaning the agent ingests untrusted third-party/public content that could influence subsequent actions.