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