carousel-generator
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data provided by the user to generate slide copy and downstream AI prompts.
- Ingestion points: The skill instructions in SKILL.md indicate it takes a 'raw topic, script idea, YouTube video, or rough notes' as primary input.
- Boundary markers: There are no explicit instructions to use XML tags, delimiters, or 'ignore' commands to isolate user-supplied text from the agent's core instructions.
- Capability inventory: The skill possesses the capability to generate text copy and construct executable prompts for external AI tools (ChatGPT Image 2), which could be manipulated by instructions hidden in the user's source material.
- Sanitization: The skill lacks any sanitization or validation steps to check user input for malicious command patterns before interpolation into the generation phases.
Audit Metadata