finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which represents a theoretical injection surface, though the current implementation is restricted to benign workflow management.
- Ingestion points: Reads configuration from
.agent/config.ymland branch information viagitcommands inSKILL.md. - Boundary markers: No explicit delimiters or boundary markers are used to isolate configuration data from the rest of the instructions.
- Capability inventory: The skill executes version control commands (
git), repository management tools (gh), and various language-specific test runners (npm,cargo,pytest,go) across all workflow options. - Sanitization: Configuration values are used directly to toggle internal logic (like
auto_commit) without additional validation or sanitization.
Audit Metadata