yy-create-rule
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses file-writing tools to create documentation directories and update Markdown files (Step 2, 3, 6). These operations are restricted to project documentation management and do not involve arbitrary shell command execution or system-level modifications.
- [DATA_EXFILTRATION]: No network activity, outbound requests (curl, wget), or data exfiltration patterns were detected. The skill interacts solely with the local file system within the project scope.
- [PROMPT_INJECTION]: Analysis of indirect injection surface (Category 8):
- Ingestion points: The
ruleparameter in SKILL.md accepts untrusted user input to be saved as documentation. - Boundary markers: The skill instructs the agent to use Markdown headers and code blocks (Step 4) to structure the input, providing basic structural delimitation.
- Capability inventory: The skill utilizes file write and edit capabilities to persist rules locally.
- Sanitization: No explicit sanitization or filtering of the user-provided rule content is described.
- [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or access to sensitive credential files (such as .ssh or .aws) were found in the skill code or instructions.
Audit Metadata