scholar-writing

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can enter the LLM context via Phase 1 reading arbitrary repository files (e.g., README.md, existing drafts, results/logs) from a user-supplied repoPath, which may contain attacker-controlled prose; this repoContext is then used as input to later phases and thus becomes LLM-readable context.