add-venue-profile

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow runs scripts/fetch_cfp.py on a user-supplied CFP URL, and that script GETs outsider-authored public web pages and extracts their readable text (doc = ...read_text(...) then out = ...to_text(doc)), which is then used to populate the profile/LLM context—an indirect prompt-injection path.