SPACE-prd-writer

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses instructional language to maintain its persona as a product manager without attempting to bypass safety filters or override core system instructions.
  • [EXTERNAL_DOWNLOADS]: The skill uses a local template file for document structure and does not perform any remote downloads of scripts or configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect injection by processing user-provided materials like meeting notes and chat screenshots. This is considered safe as the skill's capabilities are restricted to generating structured documentation and diagrams with no execution or network access.
  • [DATA_EXFILTRATION]: The skill does not contain logic for accessing sensitive system files or exfiltrating user data to external endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:31 AM