skills/niracler/skill/workspace-init/Gen Agent Trust Hub

workspace-init

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple system commands to automate workspace setup, including git for repository management, jq for JSON processing, and the GitHub CLI (gh) for version tracking and template updates.
  • [EXTERNAL_DOWNLOADS]: The skill clones sub-repositories from user-provided Git URLs. It also fetches metadata and file updates from the official GitHub repository of the template (niracler/dev-config-template) to keep the workspace synchronized with upstream changes.
  • [REMOTE_CODE_EXECUTION]: During the environment configuration phase, the skill executes standard package managers (pip, npm, bun) to install dependencies within the cloned sub-repositories. It also runs a bundled Python validation script (scripts/validate.py) and a local setup script (./script/setup) provided by the template.
  • [PROMPT_INJECTION]: The skill processes user-provided repository names and descriptions to populate configuration files like repos.json and CLAUDE.md. While this presents a surface for indirect prompt injection, the risk is minimal as the generated content is primarily used for local documentation and configuration purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 02:07 PM