plot-workflow

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and process untrusted story text and outlines which creates a surface for potential indirect prompt injection. 1. Ingestion points: Story text or outlines provided as input. 2. Boundary markers: Absent; no specific delimiters or safety instructions distinguish story content from agent instructions. 3. Capability inventory: Uses Read and Write tools for processing. 4. Sanitization: No sanitization or validation logic is present.
  • No Executable Code (SAFE): The skill consists entirely of markdown instructions and YAML metadata without any scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM