The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various shell commands including grep, awk, and find to analyze file contents and structure.
[EXTERNAL_DOWNLOADS]: The skill leverages npx to download and run third-party auditing tools like escomplex, jscpd, ts-prune, and depcheck from the npm registry.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted source code as data.
Ingestion points: The skill reads source code from projects to identify code smells and calculate metrics.
Boundary markers: None; the skill does not use delimiters to distinguish between the code being analyzed and instructions to the agent.
Capability inventory: The skill has extensive command execution capabilities and access to external package managers.
Sanitization: No sanitization or validation is performed on the content of analyzed files before it enters the agent's context.

code-smell-detector