alterlab-pra-pr-writer

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "search the web" and "read" current news hooks, media outlet directories, industry coverage, and crisis case studies (see Workflow Step 1 and Agentic Protocol), meaning it fetches and ingests untrusted public third‑party content that informs decisions and next actions and could enable indirect prompt injection.