decision-questionnaire

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses Python scripts (questionnaire_linter.py and answer_consolidator.py) to process structured JSON data. These scripts utilize only the Python standard library and do not perform any network requests, subprocess executions, or sensitive file system operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided JSON files for questionnaires and responses. While this represents an attack surface for indirect prompt injection, the scripts strictly parse structured JSON and do not execute any content as code or instructions. The workflow involves the agent reading consolidated summaries, and the skill provides templates and design guidelines to maintain structured interaction. Ingestion points: scripts/questionnaire_linter.py and scripts/answer_consolidator.py. Boundary markers: Structured JSON format and explicit templates. Capability inventory: Data processing and summary printing. Sanitization: Uses standard JSON parsing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 03:18 AM