ov-add-paper
Warn
Audited by Snyk on Jun 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). Outsider free text can enter the LLM context when the runtime reads the user-provided paper source (e.g., a paper URL or externally supplied PDF) and then compiles it into ARA Markdown, since that paper body is outsider-authored content ingested into the agent’s generation context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata