foldseek

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION] (LOW): The skill provides an example of using curl to upload a structural file (query.pdb) to https://search.foldseek.com/api/ticket. While this is the official API for the tool, it involves sending potentially proprietary research data to a non-whitelisted external domain.
  • [COMMAND_EXECUTION] (SAFE): The Python implementation uses subprocess.run with a list of arguments rather than a shell string. This is a secure practice that prevents shell injection even if input parameters are untrusted.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill recommends installing software via conda from the bioconda and conda-forge channels. These are highly reputable and standard repositories within the scientific computing community.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: Processes external query.pdb files provided by the user or found in the environment.
  • Boundary markers: None specified for the input data or the resulting CSV output.
  • Capability inventory: Execution of the foldseek binary and reading resultant tabular data into pandas for further processing.
  • Sanitization: No sanitization of the PDB content or the tool's output is performed before it is presented back to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM