cs-brainstorm

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The agent is instructed to perform repository inspections using shell commands such as grep and glob to retrieve context from project files.
  • [COMMAND_EXECUTION]: The skill includes functionality for 'spikes' or 'minimal demos' where the agent writes and executes temporary scripts (e.g., Python or TypeScript) to verify technical constraints or API behaviors.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. 1. Ingestion points: The agent reads requirements/CONTEXT.md, .codestable/attention.md, and user-provided descriptions. 2. Boundary markers: No delimiters or 'ignore instructions' warnings are present. 3. Capability inventory: The skill can write files to the repository and execute shell commands for spikes. 4. Sanitization: No filtering or escaping is specified for the external data ingested during brainstorming.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 12:39 PM
Security Audit — agent-trust-hub — cs-brainstorm