skill-dev-workflow
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell-based tools including
gitand thegh(GitHub CLI) to automate the repository lifecycle, such as branch creation, commits, and issue tracking. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and acting upon user-provided ideas and content from GitHub issues to generate code and documentation. 1. Ingestion points: Data from idea documents and GitHub issue descriptions enters the workflow. 2. Boundary markers: None are defined to separate untrusted data from instructions. 3. Capability inventory: The skill can write files, create directories, and execute repository management commands. 4. Sanitization: No explicit content validation or sanitization is performed on ingested data.
Audit Metadata