q-eda
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute a Python script (run_eda.py) using Bash to perform statistical analysis on CSV or Excel datasets.
- [EXTERNAL_DOWNLOADS]: The skill lists standard Python libraries including pandas, numpy, scipy, and openpyxl as dependencies to be installed from the official package registry.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted user data and subsequently instructs the agent to read the processed output to write a narrative summary. 1. Ingestion points: The run_eda.py script reads user-provided files (CSV/Excel). 2. Boundary markers: The agent is instructed to read generated CSVs from the tables-eda/ folder; no explicit boundary markers or instructions are provided to the agent to disregard potential control sequences within the data. 3. Capability inventory: The agent has shell execution and file writing capabilities. 4. Sanitization: No sanitization is performed on the content of the data files before they are read back and summarized by the agent.
Audit Metadata