presentation-builder
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands using the
slides-grabCLI tool (e.g.,slides-grab build-viewer,slides-grab convert). These operations are used for building, validating, and exporting slide decks. - [EXTERNAL_DOWNLOADS]: The skill references an external tool hosted on GitHub at
https://github.com/vkehfdl1/slides-grab. While this is a third-party repository, it is the primary engine for the skill's documented functionality. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted user data to generate presentation content.
- Ingestion points: Data enters the context via user-provided materials such as briefs, documents, and spreadsheets processed in the classification step.
- Boundary markers: The instructions do not define specific delimiters or warnings to separate processed data from instructions.
- Capability inventory: The skill is granted
Read,Write, andEdittool permissions and includes instructions for shell command execution via theslides-grabutility. - Sanitization: The
references/review-and-export-checklist.mdincludes a safety check to ensure that sensitive data is removed or masked before the final export.
Audit Metadata