dashboard-and-data-product-design
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests untrusted data and utilizes sensitive capabilities, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill reads "Users, decisions, cadence, and critical tasks" from research and "Metric definitions, targets, dimensions, and freshness" from project files (SKILL.md).
- Boundary markers: There are no instructions to use delimiters or ignore embedded commands when processing these external data sources.
- Capability inventory: The "Capability Contract" in SKILL.md explicitly specifies that "Read and search" and "Query execution and rendering" are required for the skill's operation.
- Sanitization: The skill lacks mention of sanitization, validation, or filtering for the external content it processes.
- [EXTERNAL_DOWNLOADS]: The skill references external design resources for practitioners.
- Evidence: References design examples from the Eleken website to provide guidance on hierarchy and first-run prompts in SKILL.md.
Audit Metadata