javascript-game-tools
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files which constitutes an untrusted data ingestion surface. \n
- Ingestion points: Project files like
package.json,tsconfig.json, and thesrc/directory mentioned inSKILL.md. \n - Boundary markers: No explicit delimiters are defined to separate untrusted file content from instructions. \n
- Capability inventory: The skill can execute development scripts (
npm test,npm run build) and modify source code. \n - Sanitization: Instructions require input validation and explicitly forbid the agent from printing secrets found in config files. \n- [COMMAND_EXECUTION]: The skill uses standard development commands for linting and testing which are scoped to the local project environment.
Audit Metadata