skills/irpsv/ai-bro/bro-on-board/Gen Agent Trust Hub

bro-on-board

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No attempts to override system instructions or bypass safety filters were detected. The instructions are focused on guiding the user through an onboarding process.
  • [DATA_EXFILTRATION]: No sensitive file access or network operations were found. The skill searches for a project-specific 'memory bank' directory (e.g., memory-bank/index.md), which is a standard documentation pattern and does not involve accessing system credentials or private user data.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute external code. It refers to other internal commands (e.g., /bro-init-memory-bank) which is expected behavior for an integrated tool suite.
  • [OBFUSCATION]: No obfuscated content, Base64 strings, or hidden characters were detected. The use of Russian language is legitimate and appropriate for its intended audience.
  • [INDIRECT_PROMPT_INJECTION]: While the skill interacts with the repository structure to find documentation files, it does not process untrusted external data in a way that would allow for instruction injection. It primarily acts as a navigator for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:49 AM
Security Audit — agent-trust-hub — bro-on-board