skills/shihyuho/skills/push/Gen Agent Trust Hub

push

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard git commands to manage branch updates, including git remote get-url, git ls-remote, and git push.
  • [EXTERNAL_DOWNLOADS]: The documentation provides installation instructions using the npx skills add command, which fetches the skill from the author's repository (shihyuho/skills). This is a standard installation pattern for the platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as git refs, repository metadata, and remote branch names. It includes explicit security logic to mitigate indirect injection by treating file-based configurations as untrusted "task data" and requiring explicit user authorization for sensitive actions like pushing to a default branch.
  • [SAFE]: The skill demonstrates high security awareness by requiring normalized ref comparisons (e.g., refs/heads/main vs main), verifying remote HEAD SHAs after operations, and enforcing a human-in-the-loop authorization model for critical repository changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 06:35 AM