github-multi-repo

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill extensively uses the Bash() tool to execute shell commands for repository management, including cloning, branching, committing, and creating pull requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection because it processes data from external repositories and executes associated lifecycle scripts.
  • Ingestion points: The skill uses gh repo clone to pull entire repositories into the local environment and gh api to read file contents (e.g., package.json, CLAUDE.md).
  • Boundary markers: No delimiters or isolation instructions are present to prevent the agent from obeying instructions found within the files it reads.
  • Capability inventory: The skill has powerful capabilities including file system write access, network operations via GitHub API, and arbitrary shell command execution via npm test and npm update.
  • Sanitization: No validation or sanitization is performed on the content of the ingested repositories before executing their scripts.
  • [EXTERNAL_DOWNLOADS]: The skill downloads code and metadata from GitHub repositories using the gh CLI and git. It also installs and updates packages from the NPM registry.
  • [REMOTE_CODE_EXECUTION]: The practice of cloning a repository and automatically running npm test or npm update within its directory constitutes a form of remote code execution, as the test scripts and post-install hooks are defined by the remote repository's author.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 03:23 PM