Skip to main content

AI/ML / Gen AI / Controls / DEV

Least Privilege for Plugins

CCC.GenAI.CN06 · Access

Restricts the permissions of any external tools the GenAI system can call to limit the potential damage if an agent is coerced to perform unintended actions or vulnerabilities in the tools are exploited.

Related Capabilities

IDTitleDescription
CCC.GenAI.CP25Plugin IntegrationsAbility for the model to use tools to complete a model interaction. For example web search, python code execution or external maths engine.
CCC.GenAI.CP21Generate ContentAbility to generate a response given a foundation model, parameter values, and a prompt.

Related Threats

IDTitleDescription
CCC.GenAI.TH07Insecure PluginA plugin integrated with a GenAI model may contain vulnerabilities such as poor input validation or improper access control. An adversary may exploit these flaws by crafting a prompt that causes the model to pass a malicious payload to the plugin, potentially leading to system compromise, data exfiltration or privilege escalation.
CCC.GenAI.TH06Unintended Action by a Model-Based AgentA model-based agent, given the authority to execute tools or interact with APIs, may perform an action that is harmful, incorrect, or not aligned with the user's true intent in response to a prompt. This can be caused by the model misinterpreting an ambiguous prompt or being manipulated by an adversary into misusing its delegated authority.

Assessment Requirements

IDTextApplicability
CCC.GenAI.CN06.AR01When an LLM invokes an external tool (e.g., an API, a plugin), then the tool MUST operate with the least privileges required for performing its intended functionality.tlp-clear, tlp-green, tlp-amber, tlp-red

Guideline Mappings

FrameworkIDRemarks
SAIFAgent Permissions