aeo-visibility

Warn

Audited by Snyk on Jun 21, 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 is ingested into the agent’s LLM context via query_engines.py calling public answer-engine APIs (e.g., Perplexity/OpenAI/Tavily/Gemini) and returning their natural-language answer (and citations) for the host agent to score in step 3.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 21, 2026, 04:03 PM
Issues
1
Security Audit — snyk — aeo-visibility