skills/i2oland/dotfiles/git-workflow/Gen Agent Trust Hub

git-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines several shell command blocks to be executed in the user's terminal. These include standard git operations (git checkout, git commit, git status) and GitHub CLI operations (gh pr create). These commands are necessary for the skill's stated purpose of managing version control workflows.
  • [PROMPT_INJECTION]: The skill contains templates that interpolate external data (such as specification names, IDs, and summaries) into shell commands. While this follows the primary use-case, it establishes a potential surface for indirect prompt injection if the source data is controlled by a malicious actor.
  • Ingestion points: Data enters the workflow via variables like identifier, name, and summary in SKILL.md.
  • Boundary markers: Not explicitly used within the shell command templates.
  • Capability inventory: Capability to execute arbitrary git and gh commands.
  • Sanitization: The skill relies on the agent's environment to handle input validation and escaping for the generated bash scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 03:44 AM