The Agent Skills Directory

[SAFE]: The skill operates entirely within the scope of codebase auditing and technical debt management. No patterns of data exfiltration, obfuscation, or unauthorized access were identified.
[COMMAND_EXECUTION]: The skill utilizes Bash to run standard search utilities such as ag (Silver Searcher) and grep. These tools are used locally to discover code patterns and verify function usages for safe deletion.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze untrusted content (comments and string literals) from the codebase being audited. Ingestion points: Content is ingested from files via the Read, Grep, Glob, and LSP tools. Boundary markers: No specific delimiters are implemented to isolate ingested code content from the agent's instructions. Capability inventory: The skill has access to powerful tools including Bash for command execution and Write/Edit for filesystem modifications. Sanitization: No explicit sanitization or filtering of codebase content is mentioned, which is expected for a code auditing utility.

tech-debt