ssrn-econpapers

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and parse public web results (notably SSRN HTML scraping with curl and RePEc/IDEAS searches, plus Semantic Scholar/CrossRef queries) so the agent will ingest and act on untrusted, third‑party, user‑submitted content from those sites (SSRN and RePEc) at runtime.