repo-standardizer

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using gh CLI, git, jq, and python3 to audit and modify GitHub repository settings, labels, and configuration files. This includes creating commits, pushing to remote repositories, and making authenticated API calls to manage repository rulesets.
  • [INDIRECT_PROMPT_INJECTION]: The skill audits existing repository content (e.g., file existence, contents of package.json, pyproject.toml) to determine the repository's state and which templates to apply.
  • Ingestion points: Repository metadata and file contents fetched from the target GitHub repository via gh api and git.
  • Boundary markers: None explicitly used during data interpolation from the target repository.
  • Capability inventory: git operations (clone, commit, push), gh API writes (label creation, ruleset updates), and file system writes.
  • Sanitization: Employs jq for JSON parsing and a Python one-liner for URL-encoding label names, reducing the risk of injection into API paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 08:48 PM
Security Audit — agent-trust-hub — repo-standardizer