api-documentation

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

• Third-party content exposure detected (high risk: 0.80). The skill accepts and parses user-supplied API artifacts (e.g., input.source.openapi_spec, input.source.code_files, and input.source.endpoint_list) which are arbitrary/untrusted content that the agent is expected to read/interpret as part of its documentation workflow, enabling indirect prompt injection risk.