audit

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests user-generated issue content (e.g., "For issue references: fetch title and body via gh issue view" in the Non-Code Path and Phase 4 cross-referencing sections of SKILL.md), and uses those external GitHub/MCP/CLI-sourced texts as supporting context that can influence filing and reporting decisions.