The Agent Skills Directory

[SAFE]: The skill contains no malicious code, obfuscated content, or unauthorized network operations. It functions as a set of guidelines for the AI to perform static code analysis.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external code files and pull requests. 1. Ingestion points: The @$1 argument accepts external file paths and PR URLs (SKILL.md). 2. Boundary markers: No explicit delimiters are used to wrap the external content. 3. Capability inventory: The skill performs text analysis and generates code suggestions based on the input. 4. Sanitization: No sanitization or filtering of external content is specified in the instructions. This is an inherent characteristic of code review assistants.

code-review