Operon Guard

Pre-flight trust verification for AI agents. Verify behavior, detect injection vulnerabilities, check for PII leaks, and measure reliability before granting...

Operon Guard appears to do what it claims, but it must execute the agent to test it — that means running potentially untrusted code. Before using it: (1) inspect the agent source first or run tests inside an isolated sandbox (container/VM) to avoid side effects or data exfiltration; (2) prefer installing operon-guard from a trusted source only (verify PyPI package owner/signature or use an internal vetted build); (3) never use operon-guard scan as a CI gate (scan exits 0 by design) — use operon-guard test and check exit codes/trust scores; (4) be aware it will exec module top-level code and add the agent's parent/grandparent to sys.path, which can affect imports; (5) if you will evaluate many untrusted skills, run the tool in a restricted network and filesystem environment so any malicious behavior is contained.

Type: OpenClaw Skill Name: operon-guard Version: 0.2.3 The operon-guard skill is a utility for runtime verification of AI agents that includes high-risk capabilities. According to SKILL.md, the 'test', 'scan', and 'init' commands use Python's 'exec_module()' to import and execute the target agent's code, which can lead to arbitrary code execution if the tool is used on unvetted or malicious files. While the documentation explicitly warns users of this behavior and the tool's purpose is security-oriented, the inherent risk of executing untrusted code in an agent's environment warrants a suspicious classification.