architecture-foundation

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow instructs the agent to “inspect existing architecture docs, entrypoints, manifests, module trees, public APIs, open issues/PRs, and tests” (and generated/config artifacts) before proposing changes, which at runtime can include outsider-authored issue/PR/wiki/discussion text fed into the LLM context via repo content retrieval.