The Agent Skills Directory

[SAFE]: The skill's primary function is local code auditing using common development utilities. It does not perform network operations, access sensitive credentials, or utilize any form of obfuscation. All identified behaviors are consistent with its stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes external data in the form of git diff outputs, which constitutes a potential surface for indirect prompt injection from the codebase being audited. 1. Ingestion points: git diff command outputs in Step 1, Step 3, and Step 4.5. 2. Boundary markers: Absent; the skill does not use explicit delimiters to separate analyzed code from its instructions. 3. Capability inventory: Analysis performed via git, rg (ripgrep), and grep. 4. Sanitization: Absent; the skill processes raw diff content for quantitative metrics.
[COMMAND_EXECUTION]: The skill executes local shell commands such as git, rg, and grep to compute change statistics and detect modification patterns. These tools are used appropriately within the auditing workflow and do not involve unauthorized privilege escalation.

justify