The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use run_command for executing static analysis tools such as npx eslint and npx tsc. While these are standard tools for code quality, they represent a vector for local command execution.
[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because its primary function involves processing untrusted source code provided by users or external repositories.
Ingestion points: Uses the read_file and grep tools to ingest arbitrary source code into the LLM context.
Boundary markers: No explicit delimiters or system instructions are provided to the agent to distinguish between the code being analyzed and potential instructions embedded within that code.
Capability inventory: The agent possesses the capability to run shell commands (run_command) and modify files (edit_file), which could be targeted by a successful injection.
Sanitization: There is no evidence of sanitization, filtering, or instruction-stripping performed on the ingested code before it is interpreted by the agent.

code-reviewer