backend-check
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
poetry runto execute formatting and testing commands. These are standard development tools for Python and do not pose a security risk. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes modified code. 1. Ingestion points: Modified backend Python code. 2. Boundary markers: Absent. 3. Capability inventory: Command execution via Poetry. 4. Sanitization: Absent. This surface is inherent to the skill's primary purpose of code validation and is considered safe within the intended development context.
Audit Metadata