brainstorm

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious behavior or direct security threats were detected within the skill instructions.
  • [NO_CODE]: The skill consists entirely of Markdown-based instructions and does not ship with any executable code, scripts, or dependencies.
  • [PROMPT_INJECTION]: No attempts to override system instructions or bypass filters were found. The skill processes project files as an ingestion point and writes results to the 'docs/brainstorms/' directory as its primary capability, forming a low-risk indirect prompt injection surface.
  • [DATA_EXFILTRATION]: The skill does not perform network requests or attempt to access sensitive user files such as SSH keys or environment secrets.
  • [COMMAND_EXECUTION]: The workflow is purely conversational and does not involve executing shell commands or interacting with the operating system APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 06:11 AM