flutter-expert

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEMETADATA_POISONINGCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [METADATA_POISONING]: The skill's YAML frontmatter lists 'https://github.com/Jeffallan' as the author, which differs from the platform-identified author 'seltherpython'. This inconsistency in metadata is noted but does not appear to be intentionally deceptive.\n- [COMMAND_EXECUTION]: The core workflow instructs the agent to execute various Flutter CLI commands including flutter pub get, flutter analyze, flutter test, and flutter run --profile. It also suggests the use of flutter pub global activate devtools. These are standard development operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and debug user-provided Dart source code and project configurations. This creates a surface for indirect prompt injection if the user's project files contain malicious instructions aimed at the agent. \n
  • Ingestion points: User-provided Dart source files and project configuration files (e.g., pubspec.yaml) located in the working directory. \n
  • Boundary markers: None. The skill does not specify the use of delimiters or 'ignore' instructions when processing user code. \n
  • Capability inventory: The skill allows the execution of shell commands through the flutter CLI. \n
  • Sanitization: None detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:50 AM
Security Audit — agent-trust-hub — flutter-expert