agent-dev-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing local system commands to manage containers, git state, and process lifecycles.
  • Evidence: The scripts in references/bin/ utilize docker (to manage Postgres containers), git (for worktree and branch management), bun (for running the app and tests), asdf (for tool version management), gh (for PR status checks), and network diagnostic tools like lsof or ss for port picking.
  • [EXTERNAL_DOWNLOADS]: The skill fetches external tools and data required for the development environment.
  • Evidence: bin/setup invokes asdf install to ensure required language/tool versions are present and bun install to download Node.js dependencies.
  • Evidence: bin/setup and references/snapshots.md describe fetching database snapshots from Google Cloud Storage (gs:// URLs) using the gcloud utility.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could potentially contain untrusted content.
  • Evidence: bin/gc (Garbage Collector) ingests data from git worktree list and gh pr list to determine which worktrees are safe to delete.
  • Evidence: bin/setup and bin/db process database snapshots and SQL queries.
  • Sanitization: The scripts implement several safety gates, such as verifying git OIDs (Object IDs) before deleting branches and requiring explicit flags (--force) for destructive actions on the canonical database.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 05:00 PM