agentic-workflows
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches workflow prompts and instructions from the github/gh-aw repository.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Loads instructions from remote markdown files in github/gh-aw and a local .github/aw/instructions.md file.
- Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore embedded commands in the loaded content.
- Capability inventory: The skill acts as a prompt dispatcher and does not have file-write, network-send, or subprocess execution capabilities.
- Sanitization: Absent; instruction files are followed directly without validation or filtering.
Audit Metadata