brainstorm

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through its core functionality.
  • Ingestion points: The agent is instructed to research the web and the codebase to form opinions.
  • Boundary markers: There are no specific delimiters or instructions to ignore commands within the researched data.
  • Capability inventory: The skill has the ability to write thoughts and plans into text or markdown files.
  • Sanitization: The instructions lack any requirement to sanitize or validate content retrieved from external sources before it is utilized or written to files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:20 AM