together-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate documentation and code examples for using Together AI's fine-tuning, monitoring, and deployment APIs.
  • [SAFE]: Sensitive information is handled using best practices, utilizing environment variables (process.env.TOGETHER_API_KEY) rather than hardcoding credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting external data during the fine-tuning process.
  • Ingestion points: Ingests training.jsonl in SKILL.md for model fine-tuning.
  • Boundary markers: None present in the instructional code snippets.
  • Capability inventory: The skill uses Read, Write, Edit, Bash, and Grep tools.
  • Sanitization: No explicit sanitization is shown for the training data as it is intended for fine-tuning, where raw data is expected.
  • [SAFE]: All external references point to official Together AI documentation and the legitimate together-ai package.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 06:11 PM
Security Audit — agent-trust-hub — together-core-workflow-b