the-citation-auditor
Warn
Audited by Snyk on Jul 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow explicitly instructs fetching 2–3 user-provided URLs at runtime (“WebFetch: read the actual current content”), and the LLM then scores that fetched page HTML against a checklist, so outsider-authored free text from public web pages flows into the agent context (indirect prompt-injection risk).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata