breakdown-tasks

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious code or patterns detected. The skill performs standard documentation tasks by reading and writing files within the project scope.
  • [PROMPT_INJECTION]: The skill processes external design documents which constitutes an indirect prompt injection surface. 1. Ingestion points: Content is read from design.md or docs/design-decisions/*.md. 2. Boundary markers: None explicitly defined in the instructions. 3. Capability inventory: Limited to file writing; no tool execution, network access, or command evaluation capabilities were found. 4. Sanitization: No explicit sanitization of input document content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 02:03 AM