experiment:
  name: agentdojo_tool_10
  description: Tool-mediated subset for indirect and retrieved-content evaluation
  seed: 42
  sample_size: 10
  output_dir: results

dataset:
  path: data/normalized/attack_cases.jsonl

selection:
  include_sources:
    - AgentDojo
  include_attack_surfaces:
    - tool_mediated

model:
  provider: groq
  name: llama-3.1-8b-instant
  max_tokens: 256
  temperature: 0.0
  execution_mode: context_first

mitigation:
  enabled: false
  strategy: none

evaluation:
  metrics:
    - attack_success