plugin-testing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No indicators of prompt injection, data exfiltration, or obfuscation were identified. The content is strictly focused on quality assurance and plugin validation.
- [COMMAND_EXECUTION] (SAFE): The skill includes a Python script (
scripts/test_runner.py) used for basic structural validation. This script only performs filesystem existence checks for specific hardcoded files (plugin.json,agents/,skills/) and does not execute arbitrary code, make network requests, or access sensitive system directories. - [DATA_EXPOSURE] (SAFE): The skill does not access sensitive files, credentials, or environment variables. All operations are local to the provided plugin directory path.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the validation logic processes external data (plugin structure), it does not ingest or interpret the contents of those files in a way that could lead to instruction injection.
Audit Metadata