github-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
ghandgitcommands locally to manage repositories, create issues, and handle pull requests. - [EXTERNAL_DOWNLOADS]: Directs the user to install the official GitHub CLI through standard system package managers such as Homebrew, APT, and Chocolatey.
- [PROMPT_INJECTION]: A potential surface for indirect prompt injection exists because the skill automates the ingestion of external data like test failure logs and commit messages into GitHub resources.
- Ingestion points: Test stack traces and GenAI findings are used as input for the
/issuecommand. - Boundary markers: No specific delimiters or boundary warnings are documented for handling untrusted external data.
- Capability inventory: The skill executes shell commands via the
ghCLI to interact with GitHub services. - Sanitization: No explicit data sanitization or validation steps are described for the automated data processing workflow.
Audit Metadata