The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it ingests and analyzes local source code.
Ingestion points: Processes local files and project structures via commands like /analyze, /review, and /find (documented in references/usage.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating code content into prompts.
Capability inventory: The skill can write to the file system (/implement, /refactor, /document), execute tests via shell commands (/test), and perform version control operations (git).
Sanitization: No explicit sanitization or validation of ingested code content is described.
[COMMAND_EXECUTION]: The skill relies on the execution of the claude-flow CLI and standard developer tools such as git, npm, and various testing frameworks (e.g., Jest, pytest). These commands are used to manage sessions, roles, and the development lifecycle.
[EXTERNAL_DOWNLOADS]: The documentation includes instructions to download and install the claude-flow CLI tool globally via the npm package manager.

pair-programming