data-quality-auditor
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONNO_CODEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts such as scripts/data_profiler.py, scripts/missing_value_analyzer.py, and scripts/outlier_detector.py via the command line to perform data analysis tasks.
- [NO_CODE]: The Python scripts referenced in the instructions are not included in the skill package, meaning the actual implementation of the data processing logic cannot be verified for security issues.
- [PROMPT_INJECTION]: The skill processes untrusted datasets (ingestion point: data.csv). It lacks explicit boundary markers to separate data from instructions and does not specify content sanitization. The skill has capabilities for shell command execution (capability inventory: subprocess calls to python3), which could be exploited via indirect prompt injection if malicious instructions are embedded in the processed data.
Audit Metadata