ork-brainstorm

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured brainstorming and decision-making support by analyzing repository context and proposing multiple implementation approaches.
  • [SAFE]: No dangerous capabilities are detected. The skill lacks network access, privilege escalation, or persistence mechanisms. It restricts file editing until a user confirms implementation.
  • [PROMPT_INJECTION]: The skill reads repository content, which constitutes an indirect prompt injection surface. The risk is considered low as the agent's output is limited to recommendations and lacks autonomous execution capabilities.
  • Ingestion points: Repository content and existing decision records are read into context.
  • Boundary markers: No explicit delimiters or ignore-instructions are used for external data.
  • Capability inventory: Only data inspection and delegation to specific agent roles are enabled; destructive actions are absent.
  • Sanitization: The skill does not perform sanitization on the data retrieved from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 06:46 AM
Security Audit — agent-trust-hub — ork-brainstorm