deploy-public-sector-ai

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests the “learning file” content from playlists/ai-in-government-ai-engineer/learnings/... (e.g., src-001), which is outsider-authored material (a talk/notes by Eoin Mulgrew) that becomes readable text in the agent’s context via the skill’s referenced learning file.