experiment-design-planner

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured guidance for experiment design and does not contain any malicious instructions or unauthorized access patterns.
  • [COMMAND_EXECUTION]: The skill instructs the agent to create a markdown artifact at ~/phd-log/experiments/. This is a local file-writing operation that is fully transparent and consistent with the skill's stated purpose of logging research experiments.
  • [DATA_EXFILTRATION]: No network operations, external requests, or credential-harvesting patterns were found. All data remains within the local environment specified by the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research data to populate a template. While it lacks explicit sanitization, the output is a static markdown document intended for documentation, presenting no significant risk of cross-context command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 11:58 AM