flutter-audit
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and execute user-supplied Flutter source code and tests, creating an attack surface where instructions embedded in that untrusted data could override agent behavior.\n
- Ingestion points: The
SKILL.mdfile instructs the agent to read screen definitions, state management logic, shared widgets, and test files provided by the user in the working environment.\n - Boundary markers: The instructions do not specify any delimiters or safety prompts to ensure the agent treats the content of these files strictly as data, lacking a mechanism to prevent the agent from obeying instructions hidden within the code.\n
- Capability inventory: The skill explicitly directs the agent to 'Run the app' (SKILL.md) and 'inspect screenshots,' which relies on the agent's ability to execute code and process visual information from potentially malicious sources.\n
- Sanitization: There are no instructions for sanitizing, validating, or filtering the contents of the audited files before the agent interacts with them.
Audit Metadata