deep-dive

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: 0.95). SKILL.md Phase 2 ingests outsider-authored free text by fetching user-provided external links (public web pages/articles/repos/videos) and reading their full content/transcripts into the agent’s LLM context for analysis.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 15, 2026, 03:21 AM
Issues
1
Security Audit — snyk — deep-dive