dev-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user inputs and existing files to automate Git workflows and document generation.
- Ingestion points: User requests and project files processed according to instructions in SKILL.md.
- Boundary markers: The framework uses Diátaxis quadrants for structure, but lacks formal delimiters for untrusted content.
- Capability inventory: Execution of git and gh CLI tools; local file system write permissions.
- Sanitization: No explicit input sanitization or filtering is documented.
- [SAFE]: The instructions contain explicit prohibitions against documenting sensitive information such as environment variables and PII, alongside requirements for human approval for destructive Git actions.
Audit Metadata