skill-ecosystem-doctor

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

• Third-party content exposure detected (medium risk: 0.30). Skill runtime scans and reads Skill markdown/code from the local registry/projection roots (e.g., scanning SKILL.md and referenced files via scan_root/scan_resource_references during ecosystem_doctor.py / validate_ecosystem), which can include outsider-authored free text if users add poison into those local Skill sources.