afk-pr-story-flow-mermaid

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

• Third-party content exposure detected (high risk: 0.75). The required workflow reads the contents/diffs of “changed files” from the PR/branch comparison (i.e., PR body/patch content authored by an outsider), which can include free-form text that the agent ingests into the LLM context.