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: 0.90). The SKILL.md explicitly states the tool queries public sources (PubMed, arXiv, bioRxiv, medRxiv) via the Valyu API and returns full article content, URLs, and images that the agent is expected to read and act on, exposing it to untrusted public third‑party content that could carry indirect instructions.