land-pr

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

• Third-party content exposure detected (high risk: 0.78). The workflow repeatedly ingests outsider-authored free text from GitHub at runtime—e.g., gh issue view <ISSUE> --json ... body,url,labels,comments (issue body/comments) and gh pr view <PR> --json ... closingIssuesReferences (PR-provided references)—which can contain arbitrary text that the agent may include in its LLM context.