The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to perform project discovery and run various audit commands. This includes running ecosystem-standard tools such as git, npm audit, eslint, ruff, bandit, and cargo audit. The instructions specify that these tools should only be run if they are already configured or installed in the project environment.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because its primary function is to ingest and analyze untrusted data from a project's source code, documentation, and metadata.
Ingestion points: The skill uses Read, Grep, and Glob tools to ingest any file within the project directory, including source code, manifests, and documentation (as described in Workflow Steps 2 and 4).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating the content of analyzed files into the agent's context.
Capability inventory: The skill is granted Bash, Read, Grep, Glob, Edit, and Write capabilities.
Sanitization: There is no mention of sanitizing or filtering the content of the analyzed files before processing.
[EXTERNAL_DOWNLOADS]: The workflow involves running auditing tools like npm audit and npx, which may interact with well-known public package registries (e.g., npmjs.com) to check for vulnerabilities. These are considered trusted, well-known services for the purpose of a security audit.

code-analyzer