spec-code
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's Phase A workflow explicitly runs "gh issue view {N} --json title,body" to read GitHub issue content (user-generated third-party text) and then uses that content to guide implementation decisions and actions, so untrusted issue text could materially influence the agent's behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata