narrative-convergence

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md step 2, the skill reads local free-text outputs from output/.chains/*.md (up to the first 600 chars) and also parses memory/logs/*.md, where those contents were authored by other skills/users and are ingested without first selecting a specific item.