configure-workflows

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

• Third-party content exposure detected (high risk: 0.80). The skill's Execution Step 1 ("Fetch latest action versions") explicitly instructs the agent to use WebSearch/WebFetch to verify current versions from public GitHub releases pages (third‑party web content), which the agent must read and use to decide/upate workflow versions—exposing it to untrusted external content that can influence actions.