research-docs-session

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

• Third-party content exposure detected (high risk: 0.70). The skill's required steps explicitly instruct the agent to "Validate citations and media references against source URLs" and the orchestration guide/reference files mention using and labeling "community sources," which requires fetching and interpreting third-party (potentially user-generated) web content as part of its workflow.