looking-up-docs

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly queries external documentation via Context7 (mcp__context7__query-docs) and its fallback steps show WebSearch/WebFetch of public docs (e.g., "https://htmx.org/docs/"), meaning the agent ingests and acts on untrusted third-party web content as part of its decision-making.