The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash function to execute a wide range of shell commands for repository discovery, cloning, and modification using gh, git, and npm CLI tools.
[REMOTE_CODE_EXECUTION]: The skill automates the cloning of remote repositories and subsequently runs npm install, npm update, and npm test on the cloned content. This behavior allows for the execution of arbitrary code if the target repositories contain malicious instructions in their configuration or test scripts.
[EXTERNAL_DOWNLOADS]: The skill fetches code and metadata from external GitHub repositories using the gh CLI and GitHub API, which are then processed locally.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it reads untrusted data (e.g., package.json, CLAUDE.md) from external repositories and utilizes this data to drive agent actions or modify other projects.
Ingestion points: Uses gh api and gh repo clone to ingest content from user-specified or discovered repositories.
Boundary markers: Lacks delimiters or protective instructions to distinguish external data from agent commands.
Capability inventory: Possesses capabilities to execute shell commands, read/write files, and perform network operations via the GitHub API.
Sanitization: Retrieved data is used directly in subsequent commands and operations without sanitization or integrity verification.

github-multi-repo