compound-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Orchestrates workflows by executing local Python scripts within the
/a0/usr/plugins/directory and manages data via a local SQLite database.\n- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection because the skill ingests and reviews external code and documentation files; this is an inherent risk of its primary function as a code analysis tool.
Audit Metadata