Skills
Navigate
skills/midudev/autoskills/flutter-expert/Gen Agent Trust Hub

flutter-expert

Fail

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external documentation URL (https://jeffallan.github.io/claude-skills/skills/frontend/flutter-expert/) that has been flagged as malicious and blacklisted by automated scanners.
  • [COMMAND_EXECUTION]: The workflow and performance optimization guides instruct the agent to execute shell commands, including:
  • flutter pub get and flutter pub upgrade --major-versions for dependency management.
  • flutter analyze and flutter test for code quality checks.
  • flutter run --profile for performance profiling.
  • flutter pub global activate devtools for installing global development tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided code and application requirements, creating a surface for injection attacks.
  • Ingestion points: User-supplied feature descriptions, widget requirements, and existing project code.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within user-provided data.
  • Capability inventory: Access to subprocess execution via the Flutter CLI toolkit as described in SKILL.md and references/performance.md.
  • Sanitization: No sanitization or validation steps are implemented for the input data before it influences the agent's output or command parameters.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 17, 2026, 11:19 PM
Security Audit — agent-trust-hub — flutter-expert