trailmark-finding-triage

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow consumes a “candidate” from the user (e.g., file/line, SARIF excerpt, weAudit Markdown excerpt, or manual claim) and then binds/analyzes it via Step 1–4, so outsider-authored free text can be ingested directly as input (even though the downstream graph comes from the target code).