open-design-poster
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues or malicious patterns were identified. The skill implements proactive safety measures by instructing the agent not to use external image URLs and to avoid autonomous actions like printing, posting, or ordering.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided briefs and external spreadsheet files (CSV, XLSX, JSON), which is an inherent attack surface for indirect prompt injection.
- Ingestion points: User input processed via
prepare_open_design_briefand data from CSV/XLSX/JSON files used in theexport_open_design_artifacttool. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the input data are defined.
- Capability inventory: The skill uses tools that register and export files to the local file system (
register_open_design_artifact,export_open_design_artifact). - Sanitization: The instructions do not specify any validation or sanitization steps for the data processed from briefs or spreadsheets.
Audit Metadata