sglang-cherrypick

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local CLI tools like git and gh to perform automation tasks. Arguments such as target_branch and pr_numbers are validated with strict regular expressions to prevent command injection before being used in shell blocks.
  • [EXTERNAL_DOWNLOADS]: The skill fetches metadata and git objects from the official sgl-project/sglang repository on GitHub.
  • [SAFE]: No malicious patterns such as credential exfiltration, obfuscation, or unauthorized remote code execution were detected. The skill's behavior aligns with its documented purpose of managing release cherry-picks for the SGLang project.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:15 PM
Security Audit — agent-trust-hub — sglang-cherrypick