feature-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed entirely of Markdown guidelines and rule files. It does not contain any executable scripts, binaries, or automated network requests.
  • [COMMAND_EXECUTION]: The rule files (e.g., rules/pr-target-develop-branch.md) include documentation for standard version control commands such as git and the GitHub CLI (gh). These are presented as best-practice examples for human-supervised development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a process for the agent to ingest developer descriptions and existing project code to generate feature specifications. 1. Ingestion points: Developer feature descriptions and automated codebase analysis (Core Workflow). 2. Boundary markers: The skill enforces a strict document structure with mandatory metadata blocks, tables of contents, and defined sections to delimit information. 3. Capability inventory: The instructions reference version control commands (git, gh) to manage pull requests. 4. Sanitization: Risks are mitigated by the mandatory 'Review' and 'Approval' steps in the defined collaboration loop, ensuring human oversight of all generated content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:41 PM