brainstorming-partner

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides structured brainstorming guidelines and uses only standard conversation and web tools. No malicious scripts or configurations were found.
  • [NO_CODE]: The skill does not contain any executable scripts or binary files, consisting only of instructions and metadata.
  • [PROMPT_INJECTION]: The skill references the use of WebSearch and WebFetch for research (SKILL.md). 1. Ingestion points: Untrusted external data via WebSearch and WebFetch. 2. Boundary markers: Absent. 3. Capability inventory: No scripts or system commands present in the skill. 4. Sanitization: Absent. This surface for indirect prompt injection is considered low risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM