board-deck-builder
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were detected in the skill's instructions or supporting scripts.
- [COMMAND_EXECUTION]: The skill provides three helper scripts (
board_prep_checklist.py,deck_structure_validator.py, andmetrics_dashboard_generator.py) designed for local data formatting. These scripts utilize only Python's standard library for JSON and CSV parsing, arithmetic calculations, and string formatting. They do not invoke shell commands, perform network operations, or interact with sensitive file paths. - [DATA_EXPOSURE_AND_EXFILTRATION]: There is no evidence of hardcoded credentials, secret harvesting, or data exfiltration. The skill processes project-related metrics and timelines without accessing environment variables or credentials files (e.g., .env, .ssh, .aws).
- [INDIRECT_PROMPT_INJECTION]: The skill's ingestion points (loading JSON or CSV data into the utility scripts) are limited to structured data processing. The scripts do not interpolate untrusted content into agent prompts or execute it as code, minimizing the risk of instruction injection.
Audit Metadata