The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository and pull requests to generate documentation and comments.- Ingestion points: Reads data from PR descriptions, code diffs, and local project files (spec, plan, decision logs).- Boundary markers: Absent. There are no instructions to the agent to treat external content as data only or to ignore embedded instructions.- Capability inventory: Uses gh (GitHub CLI) and glab (GitLab CLI) to perform actions like posting comments to remote repositories.- Sanitization: Absent. The skill does not validate or sanitize the content before using it to construct comments or guides.- [COMMAND_EXECUTION]: The skill provides instructions for using version control CLI tools (gh and glab). While these tools are used for their intended purpose, the fact that their input is derived from untrusted pull request data creates an attack surface for command manipulation.

pr-reviewer-guide