social-media-context

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly asks the user to supply "3–5 real posts" from social platforms (Step 3, Section 7 "Example posts") which are copied verbatim into .agents/social-media-context.md and read by other skills to drive writing behavior, so untrusted user-generated social-media content is ingested and can influence subsequent actions.