flutter-feature-dev
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow depends on reading and analyzing external data (user requests and existing project code) to generate implementation plans and code, which constitutes a surface for indirect prompt injection.
- Ingestion points: External data is ingested during the initial request processing (Step 1) and the discovery phase (Steps 2-4) where the agent inspects the codebase for structure and patterns.
- Boundary markers: The workflow lacks explicit instructions or delimiters that would prompt the agent to ignore potentially malicious instructions embedded within the codebase being analyzed.
- Capability inventory: The skill enables the agent to execute shell commands (
flutter test,flutter analyze,dart format) and perform file system modifications across multiple directories (lib/,test/,docs/). - Sanitization: There are no specified procedures for sanitizing or validating content retrieved from the existing codebase before it influences the agent's output or logic.
Audit Metadata