new-operation

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the shell tool to run local scripts including ./repo.sh build and ./repo.sh test. These actions are necessary for verifying the generated plugin and are limited to the user's local repository environment.
  • [PROMPT_INJECTION]: The skill interpolates user-provided metadata into code templates and verification commands. 1. Ingestion points: User-provided inputs for operation key and display names. 2. Boundary markers: Absent. 3. Capability inventory: Uses Write for file generation and Shell for local script execution. 4. Sanitization: Absent. This interpolation is the core functionality of a scaffolding tool and is considered a safe implementation within this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 07:55 AM
Security Audit — agent-trust-hub — new-operation