release-cherry-pick

Warn

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs direct shell interpolation of variables such as <VERSION> and pull request metadata (<NUM>, <SHA>) into commands like git checkout, git push, and gh pr view. This creates a command injection risk where crafted input could execute arbitrary shell commands.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting and acting upon untrusted data from the GitHub API.
  • Ingestion points: Pull request titles and metadata fetched via gh api in Step 2.
  • Boundary markers: None identified; the data is used directly in subsequent commands.
  • Capability inventory: The skill possesses significant capabilities including local filesystem modification via git and remote repository modification via gh (creating PRs, editing labels, pushing branches).
  • Sanitization: No sanitization or validation of the fetched PR titles or numbers is performed before they are included in the gh pr create and gh pr edit commands in Steps 6 and 7.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 6, 2026, 01:46 PM
Security Audit — agent-trust-hub — release-cherry-pick