The Agent Skills Directory

Command Execution: The skill instructs the agent to run local git commands (git remote get-url origin and git rev-parse --abbrev-ref HEAD) to resolve repository metadata. This information is used to facilitate linked citations in the generated documents.
Indirect Prompt Injection Surface: The skill analyzes repository files such as build configurations and source code to generate stakeholder-specific guides. This process involves the ingestion of untrusted data, which is an inherent surface for indirect prompt injection. (1) Ingestion points: Project build files (e.g., package.json, pyproject.toml) and source code within the local repository. (2) Boundary markers: The instructions do not define specific delimiters for parsed code segments. (3) Capability inventory: The agent reads local files, executes git commands, and writes new markdown files to the local file system. (4) Sanitization: There are no explicit instructions for sanitizing or escaping content extracted from the repository before it is formatted into the final guides.

wiki-onboarding