agent-web-compatibility

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and audits external website URLs (e.g., "Audit this restaurant website for AI agent compatibility: https://example.com") and its SKILL.md/README verification steps require crawling and checking public sources (Google search, Perplexity, aggregator listings like Justdial/Sulekha and site HTML/dateModified), so the agent is expected to fetch and interpret untrusted third‑party web content as part of its workflow.