type-safety-rules
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of documentation and ripgrep search patterns aimed at improving TypeScript code quality and security by identifying unsafe type-system patterns.
- [SAFE]: The provided search patterns (e.g., searching for ': any', 'as unknown as', or 'process.env') are standard static analysis techniques and do not involve execution of untrusted code or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs an agent to ingest and analyze untrusted TypeScript source code from a user's repository.
- Ingestion points: TypeScript source files (.ts) and configuration files (tsconfig.json) provided by the user.
- Boundary markers: The instructions do not define specific delimiters to separate code content from instructions for the agent.
- Capability inventory: The skill uses file searching (ripgrep). It does not request or use capabilities for network access, file writing, or arbitrary command execution.
- Sanitization: No sanitization of the analyzed code is described; however, the agent's tasks are limited to pattern detection and reporting based on the provided rules.
Audit Metadata