refactor-dart-dot-shorthands

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local developer tools including dart analyze, dart test, and a project-specific script dart tool/ci.dart. These are standard tools used for code validation within the Dart development ecosystem and their use is consistent with the skill's stated purpose of refactoring code.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes code files (.dart files within pkgs/) which represents an attack surface for indirect prompt injection.
  • Ingestion points: The agent recursively reads .dart files in a target package to identify shorthand opportunities.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potential instructions that might be embedded in the code comments or strings of the files being refactored.
  • Capability inventory: The skill possesses the capability to write to the file system (refactoring code and updating a progress file) and execute shell commands (dart analyze, dart test, dart tool/ci.dart).
  • Sanitization: The skill does not implement specific sanitization or escaping of the code content before it is processed by the agent. However, as the author is a trusted vendor and the instructions are narrowly scoped to a specific syntax transformation, the risk is minimized.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 02:26 PM