brave-man

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no executable scripts, binaries, or automated commands. It relies entirely on natural language instructions to guide the agent's behavior during a user interview.
  • [SAFE]: No external dependencies, remote script downloads, or third-party package installations were detected.
  • [SAFE]: The skill does not access sensitive local files, environment variables, or hardcoded credentials.
  • [SAFE]: There are no network operations or data exfiltration vectors present in the instructions.
  • [SAFE]: The skill is designed to produce a text-based project specification (prompt.md) and explicitly instructs the agent not to execute code or scaffold projects within the current session, which follows security best practices for session isolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:43 AM
Security Audit — agent-trust-hub — brave-man