yzr-coding-style
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes system tools such as
grepandlintto perform mechanical analysis on the code under review. These tools are used to calculate metrics like line counts, parameter counts, and nesting depth as part of the style enforcement process. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing external data in the form of code files and git diffs, which constitutes an indirect prompt injection surface.
- Ingestion points: Code snippets, files, and git patches are read into the agent's context during the review and write workflows.
- Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the analyzed code, although it specifies structured prompt segments for sub-models in
ref/multi-model.md. - Capability inventory: The skill has capabilities for file system read access, static analysis tool invocation, and multi-model orchestration via a harness subagent. It does not demonstrate arbitrary shell execution or network exfiltration capabilities.
- Sanitization: There are no explicit sanitization or escaping protocols mentioned for the content of the code files being processed.
Audit Metadata