experiment:
  name: hackaprompt_direct_10_mitigated
  description: Direct-attack subset with surface-aligned mitigations enabled
  seed: 42
  sample_size: 10
  output_dir: results

dataset:
  path: data/normalized/attack_cases.jsonl

selection:
  include_sources:
    - HackAPrompt
  include_attack_surfaces:
    - direct
  require_expected_target: true

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

mitigation:
  enabled: true
  strategy: surface_aligned
  options:
    strict_mode: true
    sanitize_untrusted_content: true
    block_suspicious_tool_actions: true
    guard_tool_outputs: true
    allow_urls_in_output: false

evaluation:
  metrics:
    - attack_success