The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands using the Bash tool to perform its primary functions. This includes checking git repository status (git rev-parse), auditing packages (npm outdated, npm audit), and running the project's test suite with coverage reporting (npx vitest, npx jest, npm test). While these are standard operations for a code review tool, they represent high-privilege operations within the agent's environment.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a vulnerability surface by ingesting and processing untrusted data from the codebase being reviewed to generate its scores and reports.
Ingestion points: The skill reads all .ts and .tsx files in the application, as well as configuration files like package.json and dependency lockfiles.
Boundary markers: The instructions do not include specific boundary markers or "ignore instructions" directives to prevent the agent from being influenced by natural language instructions found in code comments, TODOs, or metadata within the reviewed project.
Capability inventory: The skill possesses Bash (command execution) and Write (file system modification) capabilities, which could be misused if the agent is manipulated by injected content.
Sanitization: There is no mention of sanitizing or filtering the content of the reviewed files before the agent processes them for scoring and report generation.

flows-code-review