flutter-riverpod-expert
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill includes an absolute local filesystem path ('/Users/pablito/EVOworkspace/flutter/CesarferPromotoresFlutter/promotores/RIVERPOD_2025_BEST_PRACTICES.md') in the Reference section. This exposes details about the author's local directory structure and development environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and provide feedback on user-supplied code and architecture, creating an ingestion point for untrusted data. It lacks explicit instructions or boundary markers to prevent the agent from executing instructions potentially hidden within the user's input.
- Ingestion points: Analyzes user-provided Flutter code snippets and architectural queries.
- Boundary markers: None present to distinguish user data from agent instructions.
- Capability inventory: Advises on code structure and suggests standard build commands like build_runner.
- Sanitization: No input validation or filtering of external content is specified.
Audit Metadata