ian-handdrawn-ppt

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and references are focused on narrative planning and visual style management for image generation. No malicious patterns or security vulnerabilities were identified.
  • [COMMAND_EXECUTION]: The skill uses document processing tools to extract content from files like .docx and .pdf. These operations are within the scope of its defined functionality.
  • [DATA_EXFILTRATION]: No sensitive file access or unauthorized network communication patterns were detected. The skill does not attempt to access credentials or environment variables.
  • [PROMPT_INJECTION]: The skill processes external data (PDF, DOCX, etc.) as source material.
  • Ingestion points: User-provided documents and text are ingested in the workflow defined in SKILL.md.
  • Boundary markers: No explicit delimiters are used to wrap source content, which is a common surface for indirect injection.
  • Capability inventory: The skill's capabilities are limited to reading documents and generating images, posing a low risk to the system.
  • Sanitization: There are no specific instructions for sanitizing or filtering instructions that might be embedded in user-provided content.
  • [REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of external code or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 05:57 PM