The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes common shell utilities like find, wc, sort, and tail to generate file size reports and project health metrics. It also references development tools like tsc and npm audit to check for compilation errors and known security advisories. These commands are consistent with the skill's primary purpose.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes untrusted data from external project files.
Ingestion points: Project source code, package.json, README.md, and other documentation files identified during the scope detection and review phases.
Boundary markers: None. There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within the reviewed files.
Capability inventory: The skill uses shell execution and file system access to perform its analysis.
Sanitization: The skill does not perform any sanitization or validation of the text content extracted from the reviewed project files.

code-reviewer