test-driven-development

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to utilize a terminal tool to run test commands (specifically pytest). This is appropriate for the skill's stated purpose of facilitating test-driven development and does not involve unauthorized or hidden command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes the delegate_task function to pass instructions to subagents, which involves prompt interpolation of task goals and context (ingestion points). While the skill lacks explicit boundary markers or sanitization within the delegation template, it defines a rigid procedural framework and verification checklists to maintain code integrity across agent interactions. The agent possesses terminal and file capabilities (capability inventory).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 01:00 PM
Security Audit — agent-trust-hub — test-driven-development