skills/buiducnhat/co-drew/brainstorm/Gen Agent Trust Hub

brainstorm

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized network operations were detected in the skill instructions or supporting templates.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads local project files and ingests user input. However, the impact is low as the skill's capabilities are limited to documentation (docs/brainstorms/) and it requires user confirmation through the Question Tool before proceeding between phases.
  • [DATA_EXFILTRATION]: While the skill gathers project context from implementation files, it does not perform any network operations to transmit this data externally.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 11:23 AM
Security Audit — agent-trust-hub — brainstorm