The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local scripts and Ruby commands using the Bash tool to perform static analysis. Specifically, it runs bin/brakeman, bin/bundler-audit, and bundle exec rubocop. These are standard development tools for Rails applications.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of project source code that may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Reads source code and project files using the Read, Grep, and Glob tools.
- Boundary markers: Absent. There are no instructions for the agent to ignore or delimit instructions found within the code being reviewed.
- Capability inventory: Includes Bash for command execution, alongside file system access tools (Read, Grep, Glob).
- Sanitization: Absent. The skill does not sanitize or filter the content of the files it reads before processing them.

code-review