presentation-content
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes code block templates that reference an installation command (
npx skills add vercel-labs/agent-skills) for resources provided by a well-known organization. This reference is part of the illustrative slide content and is not an instruction for the agent to execute code. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform untrusted user input (referred to as "ideas" or "verbose explanations") into slide content.
- Ingestion points: User-provided text passed to the agent when using the slide drafting templates in
SKILL.md. - Boundary markers: The templates do not utilize specific delimiters or warnings to ignore embedded instructions in the user-provided ideas.
- Capability inventory: The skill is limited to text generation and does not define any subprocess calls, file writing, or network operations.
- Sanitization: There is no explicit sanitization or filtering of the user input before it is interpolated into the slide output.
Audit Metadata