expert-instruction
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown-based documentation and reference materials without any embedded executable scripts or hidden logic.- [COMMAND_EXECUTION]: A recommendation for a command-line tool (pnpm dlx skills add oakoss/agent-skills) is provided to help users extend their agent's capabilities. This tool is sourced from the vendor's own repository and serves the primary purpose of the skill.- [PROMPT_INJECTION]: The documentation mentions typical injection phrases like 'Ignore previous instructions'. These are used specifically as examples for developers to implement defensive testing and guardrails, not as instructions for the agent to follow.
Audit Metadata