rugged-evil-tester
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase data which could contain malicious instructions designed to influence the agent.
- Ingestion points: The skill uses Read, Grep, and Glob tools to analyze files in the target directory (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: The skill utilizes Write, Edit, and Bash tools to create and execute test files (SKILL.md).
- Sanitization: Absent; the skill processes code and generates tests based on inferred logic.
- [DYNAMIC_EXECUTION]: The skill generates TypeScript test files and executes them using testing frameworks. This dynamic creation and execution of code is a core function of the automated testing utility.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run the Vitest framework and perform file system operations based on user-provided arguments and discovered code structures.
Audit Metadata