expo-framework-rule
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides educational content and coding standards for the Expo ecosystem. All code snippets use placeholder data for configuration, and the tools referenced (eas-cli, expo-doctor) are the standard, official utilities for Expo development.
- [PROMPT_INJECTION]: As the skill is designed to review and interact with project source code (matching
**/expo/**/*.*), it possesses an inherent indirect prompt injection surface. Malicious instructions embedded in analyzed files could potentially influence agent behavior during code reviews. This is a common risk for code analysis tools and is mitigated by the agent's core safety guardrails. - [DATA_EXPOSURE]: The skill includes a 'Memory Protocol' that instructs the agent to read context from
.claude/context/memory/learnings.md. This is a documented pattern for state persistence in agentic workflows and does not represent an unauthorized data access attempt.
Audit Metadata