gr-geo-cite

Warn

Audited by Snyk on Jul 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). Yes—scripts/weekly-cite-check.py sends fixed queries to external LLM APIs and then ingests the returned free-form answers (ans) into the agent’s runtime context for parsing/reporting (e.g., snippet_head, context_snippet), which can contain outsider-authored text and prompt-injection payloads.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 16, 2026, 05:43 AM
Issues
1
Security Audit — snyk — gr-geo-cite