brainstorm-logos

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill follows best practices for instruction-based task execution.\n- [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection because it is designed to read and analyze external content.\n
  • Ingestion points: The instructions in SKILL.md (Phase 1) guide the agent to ingest data from files, Google Drive, and previous conversations.\n
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when processing external data.\n
  • Capability inventory: The skill uses local reference files for its frameworks and focuses on text analysis.\n
  • Sanitization: No data validation or sanitization steps are specified for the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:24 AM
Security Audit — agent-trust-hub — brainstorm-logos