respond-to-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: 1.00). The skill explicitly fetches and reads GitHub issue title/body and comments using
gh issue view ...on the NVIDIA/Megatron-LM repo, which ingests untrusted, user-generated content that the agent interprets to decide responses and next actions, creating a clear vector for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata