necromancer

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

• Third-party content exposure detected (high risk: 0.85). The skill reads GitHub Issue body text for outsider-authored items (e.g., gh issue list ... --json number,title,body,...), and that body is then ingested into the agent’s LLM context for re-evaluation, creating an indirect prompt-injection path from issue authors.