skills/bntvllnt/agent-skills/workflow/Gen Agent Trust Hub

workflow

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate development workflow designed to improve code quality and production readiness through structured planning and validation.
  • [COMMAND_EXECUTION]: The skill executes shell commands for linting, building, and testing by auto-detecting the project's technology stack (e.g., npm, pytest, go test). These operations are core to the 'ship' and 'done' actions and are performed on the user's local codebase.
  • [DATA_EXPOSURE]: Includes security-focused review perspectives and quality gates that scan for hardcoded secrets and insecure environment variable management to protect the project.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external data (user ideas and codebase files) which could theoretically contain adversarial instructions. However, the skill mitigates this through a structured 'spec-first' approach that enforces strict mapping between acceptance criteria and implementation scope.
  • [PERSISTENCE]: Implements a 'memory-update' protocol that allows the agent to suggest persistent updates to configuration files (e.g., CLAUDE.md, .cursorrules) based on session learnings. This is a documented feature for workflow optimization and explicitly requires the user to review and approve every change before it is written to disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 04:39 PM