outsourcing

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 0 triage explicitly instructs using one-shot AI agent runs (see "Can a one-shot AI agent run do this? ... /deep-research") that use file or web access to search and extract information from public sites (examples include "Find 30 wedding venues" and Step 4's instruction to search Idealista, Spotahome, Flatio, AirBnB), meaning the agent will fetch and interpret untrusted, user-generated third-party content that can change subsequent actions.