econ-visualization
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions and example code facilitate the processing of user-provided datasets, which introduces a standard attack surface for indirect prompt injection.
- Ingestion points: The example code uses the
read_csv("data.csv")function to load external data into the analysis context in bothSKILL.mdandindex.md. - Boundary markers: The instructions do not define specific delimiters or safety warnings to prevent the agent from accidentally executing instructions embedded within the processed data.
- Capability inventory: The skill allows for file reading operations and file writing via the
ggsavefunction for exporting charts. - Sanitization: There are no explicit requirements for sanitizing or validating the contents of external data files before they are processed by the agent.
Audit Metadata