complexa-design

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run the complexa CLI and related Python modules (e.g., complexa design, python -m proteinfoundation.generate). These tools are specific to the nvidia-bionemo vendor and are used to orchestrate complex scientific simulations.- [INDIRECT_PROMPT_INJECTION]: The skill accepts user input for parameters like Target name and Run name via AskUserQuestion and interpolates them directly into shell commands. This creates an attack surface where malicious input could influence command execution.
  • Ingestion points: Target name, Run name, Search algorithm, and Evaluation backend are gathered from the user (SKILL.md).
  • Boundary markers: None are defined in the command construction instructions (SKILL.md).
  • Capability inventory: Shell command execution via the Bash tool (SKILL.md).
  • Sanitization: The instructions do not define methods for validating or escaping user-provided strings before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 07:53 AM
Security Audit — agent-trust-hub — complexa-design