plan

Warn

Audited by Snyk on Apr 26, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's Phase 2 "Research phase" (SKILL.md) and the Spec/Task templates (references/spec-template.md and references/task-design-guide.md) explicitly instruct researcher agents to use tools like exa_web_search_exa and a web scraper to fetch and synthesize public web/docs content, which is untrusted third-party material that the agent reads and uses to drive technical decisions and ADRs.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 26, 2026, 01:33 AM
Issues
1
Security Audit — snyk — plan