a0-debug-plugin
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands such as
ls,find, andpy_compileto inspect the plugin directory structure and verify the syntax of Python handler files. - [DYNAMIC_EXECUTION]: Employs
python -cto run inline scripts that interface with internal framework helpers to manually trigger plugin hooks likeinstalloruninstallfor debugging purposes. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with and diagnose third-party plugin data. 1. Ingestion points: Reads configuration files (
plugin.yaml,config.json) from the plugin directories. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the diagnostic prompts. 3. Capability inventory: The skill has the ability to execute shell commands and run framework-level Python code. 4. Sanitization: The skill does not implement specific sanitization or validation of the plugin configuration data before it is processed by diagnostic tools.
Audit Metadata