data-visualization
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data files and inputs which may contain untrusted content, creating a surface for potential instruction injection.\n
- Ingestion points: The workflow requires the agent to "Inspect the available files, runtime, versions, inputs" as the first step of the visualization process (SKILL.md).\n
- Boundary markers: The instructions do not specify the use of delimiters or specific warnings to the model to ignore instructions embedded within the data being visualized.\n
- Capability inventory: The skill possesses the capability to call external APIs via
sandbase_runand generate/execute code locally to satisfy visualization requests (SKILL.md, references/sandbase-api-map.md).\n - Sanitization: There are no explicit instructions provided for sanitizing, validating, or escaping data before it is processed by the agent or passed to external tools.
Audit Metadata