The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands such as npm run lint and cargo clippy based on the presence of local configuration files. Since these commands execute scripts defined within the project's own configuration (e.g., package.json), they could be leveraged to run arbitrary code if the project files are malicious.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted source code and has the capability to both modify files and execute commands.
Ingestion points: The skill reads all files within the local project directory for metric calculation and linting.
Boundary markers: No explicit delimiters or safety instructions are used to isolate user code from the agent's internal reasoning.
Capability inventory: The skill can execute shell commands through multiple build tools and perform file-write operations via its automated 'Generator-Critic' loop.
Sanitization: There is no evidence of sanitization or validation of the content read from files before it is processed or used to generate code fixes.

review-code-quality