slides-preview
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the @marp-team/marp-cli Node.js package for slide rendering. This is a well-known and reputable utility within the developer ecosystem.
- [COMMAND_EXECUTION]: The skill invokes the marp CLI tool to convert Markdown source files into HTML slide decks (e.g., executing 'marp ... --html -o ....html').
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external data.
- Ingestion points: Untrusted content is read from course.json (SKILL.md, Step 1).
- Boundary markers: There are no explicit delimiters or instruction-ignore warnings defined for the data imported into the slide templates.
- Capability inventory: The agent possesses the capability to write files to the local system and execute the marp CLI tool.
- Sanitization: The instructions do not specify any validation or sanitization procedures for the data extracted from course.json before it is processed into the final presentation output.
Audit Metadata