debug-agent
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md Step 0 ingests outsider-authored free text by accepting an ADO work item URL (via
az boards work-item show) and a GitHub issue URL (viagh issue view --comments), which at runtime returns outsider-written description/comments that are then used “as-is”/summarized into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata