mobile-performance
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the analyzed codebase (e.g., project configuration files like pubspec.yaml and package.json) and user-supplied arguments.
- Ingestion points: Mobile framework project files (Phase 1-7); $ARGUMENTS variable.
- Boundary markers: None identified in the prompt templates.
- Capability inventory: File system read (codebase investigation); File system write (telemetry logging to ~/.claude/projects/).
- Sanitization: No explicit sanitization or validation of the content read from the project files is defined.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform deep investigation of the codebase, which involves searching and reading various project files. This functionality, while necessary for the skill's purpose, increases the exposure to potentially malicious content embedded in the source code.
Audit Metadata