| 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 | |