The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill is a legitimate resource for security professionals performing variant analysis using industry-standard tools (ripgrep, Semgrep, CodeQL). The included methodology and templates follow best practices for systematic security audits.- [PROMPT_INJECTION]: The skill processes untrusted external data (the codebase being audited), which creates a potential surface for indirect prompt injection. This is an inherent risk of any code analysis tool. Ingestion points: Analyzes source code files and outputs from search tools. Boundary markers: The instructions lack explicit delimiters to distinguish between code-to-be-analyzed and instructions-to-be-followed. Capability inventory: The skill utilizes ripgrep for shell-based searching and requires read access to the project directory. Sanitization: Source code content is analyzed without escaping or filtering.

variant-analysis