software-research

Warn

Audited by Snyk on Jul 7, 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). Yes—Phase 1/4 instructs the agent to perform runtime web research (“web search/fetch inside agents” and “Real fetched sources only”), which can ingest outsider-authored free text from public pages into the LLM context for lensing and citation verification.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 7, 2026, 05:32 PM
Issues
1
Security Audit — snyk — software-research