ts-google
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to trigger on TypeScript files, type annotations, and module imports to guide refactoring and code review, creating a surface for indirect prompt injection. Malicious actors could embed instructions in comments or string literals within the code being analyzed to manipulate the agent's behavior during these tasks.
- Ingestion points: TypeScript source files (.ts) and project configuration files processed by the agent.
- Boundary markers: The skill does not establish specific boundary markers or "ignore" instructions for the untrusted code it processes.
- Capability inventory: Agents applying these rules typically have access to the file system to read and refactor code, and may have access to terminal tools for build verification.
- Sanitization: The skill provides stylistic rules but lacks mechanisms to sanitize or filter out linguistic instructions that might be present in the target codebases.
Audit Metadata