brainstorm

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to install the google-generativeai Python package. This is an official library from a well-known service provider and is used according to its intended purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes several ingestion points for untrusted data by using placeholders such as [topic], [product], and [problem] within prompt templates passed to the Gemini CLI. While this is the primary function of the skill, it represents a surface where user-supplied content could attempt to influence the model's output. The skill provides no explicit boundary markers or sanitization for these inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:25 PM
Security Audit — agent-trust-hub — brainstorm