author-skills
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a meta-framework for developing other skills, emphasizing predictability through test-driven development and rigorous pressure testing.
- [COMMAND_EXECUTION]: The skill mentions using standard local utilities such as grep, git, sed, and find for deterministic checks, as well as local Python scripts (lint-skill-length.py, etc.) for internal validation. These are standard development tools and do not involve remote code execution or privilege escalation.
- [PROMPT_INJECTION]: While the skill uses authoritative language (e.g., 'MUST', 'NEVER') to ensure adherence to its own workflow, this is a legitimate prompt engineering technique for reliability and does not attempt to bypass system safety filters or override global instructions.
- [DATA_EXFILTRATION]: No network operations or attempts to access sensitive system files (e.g., .ssh, .aws) were detected. The file access patterns mentioned (git show, /tmp/ paths in test scenarios) are standard for software development and testing.
Audit Metadata