spec-kitty-mission-review

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

• Third-party content exposure detected (high risk: 0.70). The skill’s required runtime workflow reads mission artifacts from kitty-specs/<slug>/spec.md, plan.md, tasks.md, and contracts/*.md (outsider-authored free text if those files were authored by others), and then places that prose into the agent’s LLM context for analysis.