mobile-runtime-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references technical guidelines and procedures from external GitHub repositories associated with Expo and Callstack for instructional purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data by analyzing project source code and configuration files.
- Ingestion points: The agent is instructed to read route components, package versions, and lockfiles (SKILL.md).
- Boundary markers: No explicit delimiters are used to separate ingested content from instructions.
- Capability inventory: The skill body does not contain any instructions for the agent to perform dangerous actions like executing shell commands, writing to the filesystem, or making network requests.
- Sanitization: The skill does not prescribe specific validation or sanitization steps for the analyzed project files.
Audit Metadata