research-and-teach

Warn

Audited by Snyk on Jul 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). The workflow explicitly instructs the agent to “Fetch sources” via a WebFetch step (SKILL.md lines 12-14), which at runtime can ingest free text from publicly fetched web pages authored by outsiders into the LLM context, creating an indirect prompt-injection risk.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 21, 2026, 09:13 AM
Issues
1
Security Audit — snyk — research-and-teach