alterlab-alphafold

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill initiates the download of AlphaFold2 network weights, which are several gigabytes in size. This is a legitimate and necessary step for the local execution of the folding models.
  • [DATA_EXFILTRATION]: By default, the skill sends protein sequences to a hosted MMseqs2 API for genetic database searching. The documentation clearly discloses this behavior and notes that sequences are sent to a public service, which is standard practice for ColabFold users who do not maintain a local database.
  • [COMMAND_EXECUTION]: The skill uses shell commands to invoke colabfold_batch and uv run python. These commands are used to process user-provided FASTA files and manage the scientific environment, appearing consistent with the stated purpose of the skill.
  • [SAFE]: Analysis of the instructions and scripts shows no evidence of prompt injection, obfuscation, privilege escalation, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 11:25 PM
Security Audit — agent-trust-hub — alterlab-alphafold