test-driven-development

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as npm test and a local Python script scripts/aegis-workspace.py. These operations are routine for software development tasks and are scoped to the local environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It processes external data such as source code, test files, and test output during the TDD cycle.
  • Ingestion points: Reading project source code and test files (SKILL.md).
  • Boundary markers: None explicitly defined to separate instructions from the code being tested.
  • Capability inventory: The agent can execute shell commands (npm, python) and write files to the project directory.
  • Sanitization: No specific sanitization or validation of the processed code files is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 06:00 AM
Security Audit — agent-trust-hub — test-driven-development