plugin-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool. The documented intent is to perform atomic git commits at each implementation stage to track progress and provide a rollback mechanism.
  • [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing external configuration files.
  • Ingestion points: The skill reads architecture.md, plan.md, creative-brief.md, and parameter-spec.md to construct prompts for subagents.
  • Boundary markers: The orchestrator uses clear separators when prepending troubleshooting patterns to subagent prompts.
  • Capability inventory: The skill possesses the ability to execute Bash commands, Edit project files, and delegate complex tasks to other agents.
  • Sanitization: The skill relies on structured delegation and subsequent validation by a validation-agent rather than explicit string sanitization of input files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 02:32 AM