brainstorm

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user input which could be used to manipulate agent behavior.
  • Ingestion points: The [topic] argument in the /brainstorm command.
  • Boundary markers: No explicit delimiters are defined to isolate the user-supplied topic from the system prompt.
  • Capability inventory: The skill defines a file-write capability via the --export argument.
  • Sanitization: No explicit sanitization or validation logic is defined for input topics or export file paths.
  • [NO_CODE]: The skill consists of markdown instructions and metadata only, with no executable scripts or binary files provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:06 AM