tdd-workflows-tdd-cycle

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it directly embeds user-controlled data into subagent prompts.
  • Ingestion points: User input provided via the $ARGUMENTS variable is used to define tasks for multiple subagents throughout the workflow in SKILL.md.
  • Boundary markers: The skill does not use XML tags, delimiters, or specific instructions to separate the user-provided data from the agent's logic.
  • Capability inventory: The involved subagents (test-automator, backend-architect, etc.) have the capability to write and execute code, potentially allowing malicious inputs to trigger unauthorized actions.
  • Sanitization: There are no requirements for input validation or escaping of the user-provided requirements before they are processed by the system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:34 PM
Security Audit — agent-trust-hub — tdd-workflows-tdd-cycle