charting
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from databases to determine visualization strategies, creating an indirect prompt injection surface.
- Ingestion points: Database schema scanning and row sampling as described in SKILL.md.
- Boundary markers: None present in the instructions.
- Capability inventory: Automated generation and execution of SQL queries and Python/Pandas transformation code (SKILL.md).
- Sanitization: No explicit data sanitization or validation steps are provided for the ingested content.
- [COMMAND_EXECUTION]: The skill facilitates the creation and execution of data manipulation scripts (SQL and Python) to materialize charts, which is necessary for its stated primary purpose.
Audit Metadata