pandas-pro
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface identified.\n
- Ingestion points: The skill processes external tabular data sources (CSV, Excel, SQL, JSON) during loading and transformation workflows.\n
- Boundary markers: Absent; the skill does not provide instructions to the agent for delimiting data content from potentially malicious embedded instructions.\n
- Capability inventory: The skill performs data cleaning, transformation, and format conversion (writing data files).\n
- Sanitization: None; the instructions do not specify any validation or sanitization of data content before processing.\n- [SAFE] (SAFE): No evidence of malicious obfuscation, hardcoded credentials, or unauthorized network/system operations was found. The skill strictly provides expert-level pandas development guidance and constraints.
Audit Metadata