create-parallel-stories
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill generates shell commands for project management and development workflows, including
git worktree,npm install,npx nx serve,npx nx test, andgh pr create. These are intended to be executed by the developer to manage parallel feature branches. - [EXTERNAL_DOWNLOADS]: The skill facilitates the download and execution of packages from the official NPM registry via
npm installandnpx nx. It also provides documentation links togit-scm.com. These interactions target well-known, trusted services. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core workflow of parsing external project files to influence automation.
- Ingestion points: The skill reads
skills-config.yaml,docs/prd.md,docs/architecture.md, and sharded epic files to determine the structure of stories and codebases. - Boundary markers: No specific protective delimiters or "ignore instructions" warnings are utilized when interpolating data from these files into the generated output.
- Capability inventory: The skill has the capability to generate arbitrary shell commands and create/modify markdown files throughout the project directory.
- Sanitization: There is no evidence of sanitization or strict validation of the content ingested from the PRD or architecture documents before it is used to construct Git commands or story templates.
Audit Metadata