arch-skill
Warn
Audited by Snyk on Mar 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill includes an explicit "arch-external-research-agent" prompt that performs "Web-based best-practice research, write grounded notes with sources" (see Full Prompt Catalog and resources/PROMPT_INDEX.md), which requires fetching and interpreting open web content that can influence planning and actions, so it exposes the agent to untrusted third-party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata