skill-management

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

• Third-party content exposure detected (high risk: 0.90). The skill's auditing instructions explicitly require using web search and checking public GitHub/npm pages to verify APIs and gather evidence (see references/auditing-skills.md Phase 3 and related SKILL.md guidance), which means the agent will fetch and interpret untrusted, public third-party content that can influence audit decisions and fixes.