brainstorm

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest information from the existing conversation, codebase, and supplied evidence. This creates a surface where instructions embedded in external files or code comments could influence the brainstorming direction.
  • Ingestion points: Workflow Step 1 in SKILL.md explicitly references the conversation and codebase as data sources.
  • Boundary markers: No specific delimiters are defined to separate untrusted codebase content from the skill's own instructions.
  • Capability inventory: The skill body and configuration do not define any file-writing, network communication, or shell execution capabilities.
  • Sanitization: There is no mention of filtering or sanitizing content retrieved from the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — brainstorm