architecture-decisions
Warn
Audited by Snyk on Mar 25, 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 RESEARCH phase (SKILL.md and references/adr-lifecycle.md) explicitly instructs the agent to read external dependency source code, official documentation or API specifications (including listing URLs/files consulted), which pulls untrusted public third‑party content that the agent must interpret and that directly influences ADR drafting and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata