issue-create
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interfaces with the GitHub CLI to manage issues and labels. This is the primary functionality and follows standard practices for CLI tools.
- [PROMPT_INJECTION]: The skill processes requirements from local Markdown documents, introducing an indirect prompt injection surface.
- Ingestion points: Markdown files provided by the user in USDM format.
- Boundary markers: No explicit markers separate requirement content from agent instructions.
- Capability inventory: Command execution via the GitHub CLI.
- Sanitization: No specific sanitization of document content is required before command execution.
Audit Metadata