quality-gate
Warn
Audited by Snyk on Nov 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required PR/ticket workflow reads GitHub Issues and PR review feedback (acceptance criteria, "actionable review", "blocking review解消", linked Issue state), and those can be authored by outsiders on a public repository without the agent selecting a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill directs agents to create or modify
.github/workflows, required CI check structure, rulesets/branch protections, and budget/alert settings, which passes the operational-change gate, but no explicit irreversible operational loss is established, so the tier is capped at low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata