doc-research

Warn

Audited by Snyk on Mar 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: 1.00). The skill's SKILL.md workflow explicitly falls back to WebSearch and uses render.bash (references/cloudflare-markdown.md and the render.bash script) to fetch and convert arbitrary public URLs, meaning the agent ingests untrusted third-party web content that can affect its research and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 11:36 PM
Issues
1