agent-flutter-developer
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by using an unconstrained placeholder for user input. Ingestion points: User input is directly interpolated at the end of the instructions via the $ARGUMENTS placeholder in SKILL.md. Boundary markers: The skill lacks explicit delimiters or instructions for the agent to distinguish between its own system instructions and potentially malicious instructions embedded in the user-provided task. Capability inventory: The agent has capabilities to generate complex Dart/Flutter code, define native platform integrations, and suggest CI/CD configurations. Sanitization: There is no evidence of input validation or sanitization before the user input is processed as a task.
Audit Metadata