rubric
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is entirely declarative, consisting of markdown documentation and YAML examples. No executable scripts or binary files are present.
- [DATA_EXFILTRATION] (SAFE): There are no instructions or tools for network communication. Use of
read_fileandwrite_filetools is intended for local rubric management, which is consistent with the skill's purpose. - [PROMPT_INJECTION] (SAFE): No instructions designed to bypass AI safety filters or override system prompts were detected. The command set provided is limited to the skill's logical domain.
- [COMMAND_EXECUTION] (SAFE): No indicators of shell command execution, privilege escalation, or persistence mechanisms were found.
Audit Metadata