faion-ba-modeling

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill utilizes a restricted version of the Bash tool limited to 'ls:*'. This significantly limits the attack surface as it only allows for directory listing and prevents arbitrary command execution.
  • [DATA_EXFILTRATION] (SAFE): No network-capable tools are listed in the allowed-tools configuration. There are no hardcoded credentials, sensitive file paths, or external network requests found within the skill's instructions or templates.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to ingest and process user-provided documentation to generate BA artifacts. While this presents a surface for indirect prompt injection (Category 8), the risk is minimized by the lack of high-privilege execution tools.
  • Ingestion points: Processes user business descriptions via the 'Read' tool.
  • Boundary markers: Templates use structured Markdown but lack explicit 'ignore embedded instructions' markers.
  • Capability inventory: Limited to file operations (Read, Write, Edit) and basic listing (Bash ls).
  • Sanitization: No specific sanitization logic is implemented for processing external text inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM