deepspot-m

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the deepspotm library from the Python Package Index (PyPI) and the retrieval of model weights from Hugging Face. These are well-known and standard platforms for software and model distribution.
  • [COMMAND_EXECUTION]: The instructions include the use of uv pip install and huggingface-cli login. These commands are necessary for managing dependencies and authenticating access to gated model weights, adhering to standard security practices for machine learning assets.
  • [SAFE]: A comprehensive analysis across all threat categories, including prompt injection, data exfiltration, and obfuscation, found no evidence of malicious intent. The skill's operations are transparent and strictly limited to its stated purpose of performing spatial transcriptomics analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:02 PM
Security Audit — agent-trust-hub — deepspot-m