bdd-unit-test-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and formatting templates for reviewing code. It does not contain executable scripts, shell commands, or network operations.
  • [PROMPT_INJECTION]: No evidence of jailbreak attempts, system prompt extraction, or safety bypass instructions was found. The use of 'CRITICAL' in the document refers to a severity scale for code review findings, not a security override.
  • [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files or environment variables. No network requests are initiated.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided test code. While this represents a potential attack surface for indirect prompt injection (where instructions are hidden in the code being reviewed), the skill's scope is restricted to generating a text-based review and does not possess capabilities like file system writes or code execution that could be abused by such an injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 01:32 AM
Security Audit — agent-trust-hub — bdd-unit-test-reviewer