create-issue
Warn
Audited by Snyk on May 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to fetch and parse logs, PRs, commits, and issue lists from the public GitHub repo (e.g., via
gh api repos/NVIDIA/Megatron-LM/actions/jobs/<job_id>/logs,gh pr view, andgh issue list), which are untrusted, user-generated third-party contents that the agent must interpret to decide whether to create or assign issues.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata