agentic-workflows
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches workflow prompts and configuration files from the
github/gh-awrepository. These resources are from a well-known service provider and are essential for the skill's documented purpose of providing specialized workflow instructions. - [INDIRECT_PROMPT_INJECTION]: By loading and following instructions from a remote repository, the skill possesses an indirect prompt injection surface. The agent is instructed to load external Markdown files and follow them directly as new instructions.
- Ingestion points: Multiple files located within the
.github/aw/directory of thegithub/gh-awrepository are loaded into the agent's context. - Boundary markers: None provided; the skill relies on the content of the loaded files to drive agent behavior without explicit isolation.
- Capability inventory: The skill facilitates complex tasks including workflow creation, debugging, and optimization, which likely involve file system and command execution tools depending on the specific prompt loaded.
- Sanitization: None; the skill assumes the integrity of the remote content hosted on the official GitHub repository.
Audit Metadata