agentic-workflows
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a router for GitHub Agentic Workflows, identifying user intent (design, create, update, debug) and loading the corresponding task-specific prompt.
- [EXTERNAL_DOWNLOADS]: Fetches workflow prompts and configuration files from the official
github/gh-awrepository. These references are used to provide the agent with the necessary context for managing agentic workflows. - [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism to load repository-specific instructions (
.github/aw/instructions.md) which can override default prompts. This is a standard customization feature for workflow automation.
Audit Metadata