ccc-brainstorm

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a structured ideation template. It uses the Agent tool to spawn sub-processes for analysis and the AskUserQuestion tool for interaction. While it accepts user-provided topics and codebase context, which is a standard surface for Indirect Prompt Injection, the skill's purpose is strictly conversational and analytical, with no instructions to perform state-changing operations or sensitive data exfiltration. The presence of the Bash tool in the allowed-tools list is a platform-level configuration and is not used by the skill's logic for any dangerous commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 06:07 AM
Security Audit — agent-trust-hub — ccc-brainstorm