qa-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard
grepcommands to search for specific code patterns (such as@ts-ignore,: any, andconsole.log) within thesrc/directory. These commands are static, hardcoded, and do not involve the execution of untrusted external input or scripts.\n- [PROMPT_INJECTION]: The skill processes external source code files as part of its code review workflow, which creates a surface for indirect prompt injection.\n - Ingestion points: The agent reads and reviews files changed in the current task context (SKILL.md).\n
- Boundary markers: No specific delimiters or instructions to ignore embedded agent commands are used when reading files.\n
- Capability inventory: The skill uses
grepfor pattern identification across the ingested content.\n - Sanitization: No sanitization or validation of the file content is performed prior to processing. Note: This risk is considered low as it is inherent to the skill's primary function of code analysis.
Audit Metadata