geo

Warn

Audited by Snyk on Jul 15, 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 for /geo audit <url> fetches arbitrary outsider web content (homepage HTML, sitemap/internal pages, robots.txt, and llms.txt/llms-full.txt) via scripts/fetch_page.py, which produces readable text fields (e.g., text_content, robots.content, llms_txt.content) that are then used by the agent to synthesize reports—creating an indirect prompt-injection path from outsider-authored page/robots/llms text into the LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 15, 2026, 12:54 PM
Issues
1
Security Audit — snyk — geo