chirp

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to open and snapshot public X/Twitter pages (e.g., https://x.com/home, profile and status URLs, and search results) via the OpenClaw browser, so the agent will ingest untrusted, user-generated social media content that could carry indirect prompt injection.