cwicr-data-loader

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface because it is designed to ingest and process untrusted external data files (CSV, Excel, JSON, and Parquet).
  • Ingestion points: The _load_csv, _load_excel, _load_json, and _load_parquet methods in SKILL.md read data from user-specified file paths.
  • Boundary markers: The implementation lacks explicit delimiters or instructions to the agent to ignore embedded natural language commands within the processed data.
  • Capability inventory: The skill performs filesystem read and write operations via the load and export methods in the CWICRDataLoader class.
  • Sanitization: No sanitization or filtering of text content within the data files is performed to prevent the agent from interpreting embedded text as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:27 AM