trtllm-flashinfer-upgrade
Warn
Audited by Snyk on May 20, 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's Step 1 explicitly fetches release data from the public GitHub page (https://github.com/flashinfer-ai/flashinfer/releases) or the GitHub API and parses tag names/dates which the agent then uses to choose a target version that directly drives repository edits, commits, pushes, and PR creation, so untrusted third‑party content can materially influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata