core-coding-standards
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, hardcoded credentials, or unauthorized system access attempts were found. The skill content is limited to instructional documentation on coding best practices and organization.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as its primary function involves processing untrusted code for review.\n
- Ingestion points: The skill is triggered to review code provided in the user's project context (SKILL.md).\n
- Boundary markers: There are no specific delimiters or instructions defined to isolate the rules from the code being analyzed.\n
- Capability inventory: The agent is permitted to use Bash, Read, Write, Edit, Grep, and Glob tools for file manipulation and analysis.\n
- Sanitization: No mechanisms for sanitizing or validating the input code are described in the guidelines.
Audit Metadata