prompt-improver

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

• Third-party content exposure detected (high risk: 0.90). The skill's required research phase (SKILL.md Phase 1 and references/research-strategies.md) explicitly instructs the agent to use WebFetch/WebSearch to read online documentation and best-practice web content and to ground questions/decisions on those findings, which means untrusted public third‑party webpages can be ingested and materially influence subsequent actions.