langsmith-graph-evaluator

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill creates evaluators that ingest data from application runs (inputs and outputs) and interpolate them directly into LLM prompts. This creates a surface where potentially adversarial content within the processed data could influence the evaluator's judgment.
  • Ingestion points: Untrusted data enters the agent context via the Run.inputs, Run.outputs, and thread.runs objects in SKILL.md.
  • Boundary markers: The provided prompt templates use direct variable interpolation (e.g., {{answer}}) without explicit boundary markers or instructions to ignore embedded commands.
  • Capability inventory: The skill executes Python logic within @node functions and performs network operations to interface with LLM providers.
  • Sanitization: The instructions do not describe explicit sanitization, escaping, or filtering of the external content before it is interpolated into prompts.
  • [Dependency Management]: The skill guides the user to install external Python packages like openevals and langchain-anthropic. These are standard dependencies for building evaluators within this ecosystem.
  • [Credential Safety Practices]: The skill provides instructions for managing API keys using environment variables and workspace secrets. It follows a safe practice by explicitly advising against hardcoding sensitive credentials in source files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 07:25 PM