client-package-local

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md Step 1/2 instructs the agent to read arbitrary client workspace files (e.g., context.md, strategies/.md, campaigns/.md, content/.md, leads/.csv/*.json) and then copy “meaningful content” into new .md outputs, so any outsider-authored text present in those files would be ingested into the LLM context during processing.