politique-cookies-malik-taiar

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and read public third‑party content (e.g., "CONSULTER les URLs en ligne avec WebFetch" for CNIL pages and "Recherches sur le site" / benchmarking of competitor cookie policies using the client's URL), so it will ingest untrusted, user-provided or public web content as part of its workflow.