The Agent Skills Directory

[COMMAND_EXECUTION]: The skill extensively uses the gh CLI and shell commands through Bash() blocks to discover repositories, manage file systems, and coordinate development workflows across multiple projects.
[EXTERNAL_DOWNLOADS]: Clones remote repositories from GitHub using gh repo clone and uses npx to run remote packages and tools.
[REMOTE_CODE_EXECUTION]: The skill performs npm update and npm test on repositories cloned from external sources. This presents a risk where malicious lifecycle scripts or test files in a repository could execute arbitrary code on the runner.
[PROMPT_INJECTION]: The skill's metadata lists 'Claude Flow Team' as the author, which differs from the identified author 'Cornjebus'; such discrepancies can be deceptive. Additionally, the skill ingests untrusted content from remote repositories (metadata and file contents) which could contain malicious instructions designed to influence the agent's actions.
Ingestion points: Repository metadata from gh repo list and file contents (e.g., package.json, CLAUDE.md) from GitHub API calls are loaded into the agent's context.
Boundary markers: No delimiters or instructions are used to separate untrusted external data from the skill's instructions.
Capability inventory: The skill possesses capabilities for shell command execution, file system modification, and GitHub repository write access.
Sanitization: There is no validation or sanitization of content retrieved from external repositories before it is processed by the agent.

github-multi-repo