when-analyzing-skill-gaps-use-skill-gap-analyzer

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow scans and parses ~/.claude/skills/**/SKILL.md files (Phase 1: “Scan All SKILL.md Files” → “Parse YAML Frontmatter” → “Map Capabilities from Descriptions”), so any outsider-authored skill markdown present in those directories can be ingested as readable text into the agent’s LLM context, enabling indirect prompt injection.