explain-concepts

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to perform WebSearch for diagrams and to use the /deep-research skill as part of its core workflow (see "Using Images" decision flow and "Step 0: Knowledge Verification" in SKILL.md and references/methodology.md), which requires fetching and interpreting open/public web content that could be untrusted and could influence subsequent actions.