generate-issue
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Utilizes the
ghandgitcommand-line tools for repository environment validation, metadata discovery, and issue publication. These tools are used according to their standard functionality for repository management.\n- [PROMPT_INJECTION]: The skill processes data from untrusted sources like repository files and existing issues, creating a surface for indirect prompt injection.\n - Ingestion points: Project source files, README documents, commit messages, and previous GitHub issue titles and descriptions (SKILL.md Steps 1, 2, and 6).\n
- Boundary markers: Absent; the agent is not specifically instructed to ignore instructions that may be embedded within the analyzed project files or issue history.\n
- Capability inventory: The skill is authorized to create and comment on GitHub issues and manage repository labels using the
ghCLI, and it has file system read access for codebase analysis.\n - Sanitization: Absent; content retrieved from the repository is used to inform the generation of technical analysis and issue bodies without explicit filtering or escaping.
Audit Metadata