academic-reference-finder

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

• Third-party content exposure detected (medium risk: 0.65). This skill’s workflow prioritizes no-key sources and includes unauthenticated calls to public web APIs/sites (e.g., Semantic Scholar unauthenticated access, and other public REST/E-utilities) that return abstracts/snippets treated as free-text search results, which the agent can then incorporate into LLM context.