paper-doodle-courseware-ppt
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
- Ingestion points: User-provided themes, article paragraphs, and content structures processed in SKILL.md.
- Boundary markers: None identified in the prompt template or workflow.
- Capability inventory: The skill has the capability to call the image_gen tool to create 16:9 images.
- Sanitization: While the skill attempts to summarize or compress input, it lacks formal sanitization, escaping, or explicit instructions to ignore embedded commands in the user-provided data.
Audit Metadata