pipeline-security

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

• Third-party content exposure detected (high risk: 0.70). Outsider-authored free text can enter the LLM context because the required runtime workflow reads repository CI/CD configuration files and supporting security config “as potentially untrusted” (e.g., via Step 1 discovery + Step 2 “Read each pipeline configuration file”), and those files’ contents may include untrusted instructions from contributors other than the operating user.