open-design-deck-from-source
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as PDFs, spreadsheets, and repository files to generate presentation decks and outlines.
- Ingestion points: The skill is instructed in Step 1 to identify and read up to 10 workspace files, which may include external documents provided by users or found in the repository.
- Boundary markers: The instructions do not define clear boundary markers or include warnings to ignore instructions that might be embedded within the source documents.
- Capability inventory: The skill uses tools to read file content (
read_open_design_source), prepare briefs (prepare_open_design_brief), write outlines to disk (outlinePath), and register/export artifacts. - Sanitization: There is no explicit sanitization or filtering logic mentioned to prevent the agent from acting upon instructions found inside the documents being processed.
Audit Metadata