to-tickets-plus

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

• Third-party content exposure detected (high risk: 0.85). The workflow explicitly says to fetch a referenced spec/issue/URL and “read its full body and comments” (SKILL.md:11-11), which is outsider-authored free text (e.g., issue/PR/wiki/web content) that would be ingested into the agent’s LLM context at runtime.