dart-dart-format

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute the dart format . command through the dart_format MCP tool to process Dart code files.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data.
  • Ingestion points: The roots array and paths strings in the arguments schema of SKILL.md allow the agent to process external directory and file identifiers.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content are present in the prompt templates.
  • Capability inventory: The skill has the capability to execute filesystem-related commands via the dart_format tool.
  • Sanitization: The schema provides partial sanitization by requiring a file: URI scheme and stating that paths must be within allowed client roots.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 08:28 PM