start-flutter-craft
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong imperative language like 'ABSOLUTELY MUST' and 'not negotiable' to override the agent's default decision-making process and force the invocation of specific tools before answering user queries.
- [PROMPT_INJECTION]: The skill defines a workflow for processing untrusted user input to trigger other tools without explicitly defining boundary markers or input sanitization (Ingestion points: User message received; Boundary markers: Absent; Capability inventory: flutter-craft tool suite; Sanitization: Absent).
- [SAFE]: No unauthorized network requests, credential exposures, or remote code execution patterns were detected in the skill file.
Audit Metadata