brainstorm

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection by consuming untrusted data from the project's environment.
  • Ingestion points: The agent is instructed to study the current state of the project, including files, documentation, and recent commits (SKILL.md).
  • Boundary markers: The instructions do not provide delimiters or specific markers to distinguish between system instructions and data found within the project files.
  • Capability inventory: The skill has the ability to write documentation to the docs/plans/ directory based on the processed information.
  • Sanitization: No validation or sanitization of the input data is mentioned before it is used to generate design recommendations or documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:32 AM
Security Audit — agent-trust-hub — brainstorm