android-material3-compose
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a local Python script (
scripts/inspect-project.py) used to scan Android project structures for Material 3 and Compose configurations. The execution is limited to local file system reading and regex-based pattern matching. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data in the form of local project source code during its inspection phase.
- Ingestion points:
scripts/inspect-project.pyreads text content from files located within the directory provided to the--rootargument. - Boundary markers: The skill does not explicitly define markers or instructions to ignore embedded content when the agent processes the inspection results.
- Capability inventory: The skill performs local file reads and provides instructions for UI development; the included scripts do not utilize network access, subprocesses, or persistence mechanisms.
- Sanitization: The script performs read-only operations and processes file contents using static regular expressions without executing or evaluating the content as code.
Audit Metadata