enhance-mobile-native-feel
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands like
grepandripgrep(rg) to inspect the local codebase for navigation patterns, styling hacks, and library usage. - [COMMAND_EXECUTION]: It invokes specialized tools and project-specific scripts such as
mobile-emulator-start, as well as the repository's native type-checking and testing suites during the verification phase. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the local repository, creating a surface for indirect prompt injection if the source files contain malicious instructions disguised as code or comments.
- Ingestion points: Reads
package.json,.tsx,.ts,.html, and.cssfiles from the local filesystem. - Boundary markers: None identified; the instructions do not specify delimiters or warnings to ignore content within the analyzed files.
- Capability inventory: Includes file system read access, command execution (
grep,rg,npm test, etc.), and the ability to modify source code based on the findings. - Sanitization: No sanitization or validation of the ingested code content is performed before it is processed by the agent.
Audit Metadata