tdd-workflows-tdd-cycle

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill uses the $ARGUMENTS variable, which represents untrusted user input, and interpolates it directly into natural language prompts sent to various subagents (e.g., architect-review, test-automator, backend-architect). This pattern allows an attacker to inject instructions that could influence the behavior of those subagents.
  • Ingestion points: The $ARGUMENTS variable is interpolated into prompts across multiple phases (Phase 1 through Phase 6) in SKILL.md.
  • Boundary markers: There are no delimiters (such as XML tags or triple quotes) or explicit instructions to ignore embedded commands used around the $ARGUMENTS interpolation.
  • Capability inventory: The skill leverages the Task tool to invoke subagents with significant capabilities, including code generation (backend-architect), test generation and execution (test-automator), and architectural analysis (architect-review).
  • Sanitization: The instructions do not define any validation, filtering, or escaping mechanisms for the $ARGUMENTS input before it is passed to subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 02:58 PM