automation-workflows

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests and acts on arbitrary webhook payloads and external URLs (see "define triggers via ... {'trigger':'http-post','url':...}" and "expose webhooks via the skill's server (e.g., run claw server start --port 8080)"), and those untrusted third‑party payloads are used in transforms/conditional logic and chained actions, so external content can materially influence agent behavior.