tsfm-forecast

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or persistence mechanisms detected. The skill is designed for local data science workflows.
  • [EXTERNAL_DOWNLOADS]: Generates code that fetches model weights from official, trusted repositories on HuggingFace (Google, Amazon, Salesforce). These are neutrally documented as part of standard model inference functionality.
  • [COMMAND_EXECUTION]: Includes a local Python script (ts_profiler.py) for data analysis. The script features built-in input validation to prevent path traversal and shell injection attacks.
  • [PROMPT_INJECTION]: The skill instructions define clear boundaries and security tiers, including specific sanitization requirements for user-provided file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:19 AM