github-agentic-workflows
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions fetch workflow configuration and agent behavior files from the githubnext/agentics repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated content from GitHub issues and pull requests, which may contain instructions intended to manipulate the AI agent.
- Ingestion points: Untrusted data enters the agent context through issue and pull request events, as well as file reads via the github.repos.getContent tool.
- Boundary markers: The workflow templates do not utilize clear delimiters or system instructions to distinguish between agent commands and external data.
- Capability inventory: The agent can write comments, create issues and pull requests, and modify repository files.
- Sanitization: There is no evidence of data sanitization or validation performed on the ingested content.
- [COMMAND_EXECUTION]: Recommends installing the @github/gh-aw npm package and the github/gh-aw GitHub CLI extension.
Audit Metadata