create-branch
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local git commands (
git switch,git fetch,git push) and GitHub CLI commands (gh issue view,gh issue develop) to manage branches. These operations are core to the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that could contain malicious instructions.
- Ingestion points: Reads local git state via
!git diff HEADand!git loginSKILL.md, and fetches GitHub issue content viagh issue viewas described in the task instructions. - Boundary markers: The skill does not explicitly define delimiters for the interpolated data to distinguish it from instructions.
- Capability inventory: Can execute branch creation, switching, and pushing to remote repositories (via
gitandgh). - Sanitization: No sanitization of the issue body or commit messages is performed before using them to derive branch names or descriptions.
- [DYNAMIC_CONTEXT_INJECTION]: The skill uses dynamic context markers (
!) inSKILL.mdto collect environment data at load time. - Evidence:
!git status,!git diff HEAD,!git branch --show-current, and!git log --oneline -10. - Reasoning: These commands are static and used for context gathering relevant to git branch management, presenting no direct command injection risk for the load-time execution.
Audit Metadata