skills/modelstudioai/cli/bailian-opd/Gen Agent Trust Hub

bailian-opd

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied dataset files for model training, which represents a potential surface for indirect prompt injection if those files contain malicious instructions.\n
  • Ingestion points: Training and validation datasets provided via the --datasets and --validations flags in scripts/opd-preflight.mjs.\n
  • Boundary markers: No explicit markers or delimiters are used in the scripts to isolate file content from instructions.\n
  • Capability inventory: The skill executes commands via the bl CLI tool to validate datasets and manage training jobs.\n
  • Sanitization: The skill performs local schema validation using bl dataset validate --schema chatml before job submission to ensure data format integrity.\n- [COMMAND_EXECUTION]: The skill scripts execute the bl CLI tool using node:child_process.spawnSync to perform various cloud operations.\n
  • Execution logic: The implementation passes arguments as an array and disables shell execution (shell: false), which follows security best practices to prevent command injection.\n
  • Safety gates: Critical actions such as job submission are protected by a manual consent gate, requiring an explicit --confirmed flag from the user after they have reviewed a dry-run report.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 06:47 AM