dependency-scanning

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

• Third-party content exposure detected (high risk: 0.70). The required workflow reads user/project dependency manifests and lockfiles (e.g., package.json/yarn.lock/lockfiles) as free-form text for analysis, and those files can contain outsider-authored instructions or strings that the agent may incorporate into its LLM context (indirect prompt injection risk).