go-backend-dev-workflow

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates the creation and execution of shell scripts (ops-*.sh) to perform functional testing and regression (Phase 4 and Phase 6). This involves running dynamically generated commands in the local shell environment.
  • [PROMPT_INJECTION]: The workflow relies on external inputs such as session context and architectural documents to determine implementation details, creating a surface for indirect prompt injection.
  • Ingestion points: Session background, architectural design files (arch-*.md), and the task tracking file (tasks/todo.md).
  • Boundary markers: The skill does not define delimiters or specific instructions to ignore embedded commands within the ingested files.
  • Capability inventory: The agent has access to shell execution (Bash), file modification (Edit, Write), and project-specific tool calls (Agent).
  • Sanitization: No explicit validation or sanitization logic is provided for content extracted from external documents before it is used to generate implementation code or test scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 02:54 PM