aggressive-schelling

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

• Third-party content exposure detected (high risk: 0.80). The skill's scripts (scripts/schelling.sh) call the public API at https://api.schelling.sh (post_many / follow_up) and SKILL.md requires posting and capturing streamed responses/CIDs, so the agent ingests public/user-submitted content from a third-party service that can influence subsequent decisions.