test-guided-debloating
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute arbitrary test commands provided by the user and perform destructive file system operations using 'rm' to remove unused code elements.
- [PROMPT_INJECTION]: The skill possesses a significant surface for indirect prompt injection because it processes and executes code from potentially untrusted repositories. * Ingestion points: Target repository source code, test suites, and user-provided test commands in SKILL.md. * Boundary markers: No delimiters or protective instructions are used to isolate untrusted content. * Capability inventory: The skill utilizes subprocess execution for shell commands and file system modification (rm). * Sanitization: There is no validation or sanitization of repository content or test commands before execution.
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install well-known development utilities such as 'pytest-cov', 'nyc', and 'jacoco' from official package registries.
Audit Metadata