release-cherry-pick
Warn
Audited by Snyk on May 19, 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 SKILL.md explicitly instructs the agent to call the GitHub API (Step 2: gh api search/issues) and gh pr view (Step 4) to fetch public, user-generated PR data from the NVIDIA/Model-Optimizer repository and then use that data to decide which commits to cherry-pick and what subsequent git/PR actions to perform, exposing it to untrusted third-party content that could influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata