skills/nvidia/skills/openfold3-nim/Gen Agent Trust Hub

openfold3-nim

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes biomolecular sequences and Multiple Sequence Alignments (MSAs) which are interpolated into JSON payloads for structure prediction requests.
  • Ingestion points: Data enters through the sequence, smiles, ccd_codes, and msa.alignment fields in SKILL.md and references/api.md.
  • Boundary markers: Instructions do not mandate the use of delimiters or escaping when the agent incorporates user data into the request body.
  • Capability inventory: The skill performs network operations via requests.post and local file writes using open() in SKILL.md and references/examples.md.
  • Sanitization: No explicit sanitization of sequence or alignment strings is performed before payload construction.
  • [COMMAND_EXECUTION]: The skill provides shell commands for local container orchestration and service monitoring.
  • Evidence: Includes scripts in SKILL.md for registry authentication, launching the NIM container with docker run, and executing curl loops for readiness checks.
  • [EXTERNAL_DOWNLOADS]: Fetches required deployment artifacts from vendor-controlled infrastructure.
  • Evidence: Downloads the openfold3 NIM container image and model weights (10–15 GB) from nvcr.io as documented in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 02:30 PM