brainstorm-experiments

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied hypotheses to design experiments, which represents a potential surface for indirect instructions to be ingested into the agent context.\n
  • Ingestion points: Hypothesis text provided by the user in the workflow or via JSON assets like assets/sample_hypotheses.json.\n
  • Boundary markers: The instructions do not define specific delimiters or guardrails to isolate untrusted hypothesis text.\n
  • Capability inventory: Capabilities include local Python script execution (experiment_designer.py) and file generation using assets/experiment_plan_template.md.\n
  • Sanitization: No sanitization is performed on the natural language strings before processing.\n- [COMMAND_EXECUTION]: The agent is instructed to run scripts/experiment_designer.py to automate experiment method selection.\n
  • The script relies solely on the Python standard library and does not include network, shell, or sensitive file access capabilities.\n
  • The logic is limited to parsing JSON and detecting keywords using regular expressions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 03:19 AM