git-workflow
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown documentation and instructional guidelines. It does not include any scripts, automated commands, or tool configurations that execute logic.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface for version control files (e.g.,
.git/**,CHANGELOG.md,.commitlintrc*) to provide context for Git-related tasks. However, because the skill lacks any autonomous capabilities—such as file writes, network operations, or shell execution—there is no exploitable path for indirect prompt injection. - Ingestion points: Defined in
SKILL.md(.git/**,.gitignore,.commitlintrc*,.husky/**,CHANGELOG.md). - Boundary markers: None present.
- Capability inventory: None. No tools or subprocess calls are configured.
- Sanitization: Not applicable as no data is processed through executable logic.
- [DATA_EXPOSURE]: Access to
.git/**metadata is standard for the skill's stated purpose of assisting with version control workflows and does not indicate unauthorized data harvesting in this context.
Audit Metadata