The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash blocks to execute various shell commands for repository management, including gh (GitHub CLI) operations for listing and API access, git commands for version control, and npm scripts for testing and updates.
[EXTERNAL_DOWNLOADS]: The skill downloads source code from GitHub repositories using gh repo clone and fetches packages from the NPM registry using npm install and npx. While these are well-known services, the automated nature of these downloads is part of a broad execution chain.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from discovered repositories (such as package.json and CLAUDE.md), which could potentially contain malicious instructions or scripts.
Ingestion points: Repository metadata and file contents fetched via gh repo list and gh api in SKILL.md.
Boundary markers: The skill does not implement delimiters or specific instructions to the agent to ignore potentially malicious embedded content within the processed files.
Capability inventory: The skill possesses extensive capabilities across multiple files, including shell command execution (Bash), file modification (mcp__github__push_files), and GitHub API interactions to create issues and pull requests.
Sanitization: There is no evidence of validation or sanitization of the content fetched from remote repositories before it is passed to automated workflows or command execution tools (like npm test).

qe-github-multi-repo