Act Security
by Act Security
Enforce least-privilege access for humans, workloads, and AI agents in cloud environments — analyze effective IAM permissions and close the gap agents inherit from stale human roles.
Skills
Permission Analysis
Resolves effective IAM permissions across policies and boundaries to show what an identity can actually do.
Policy Simulation
Simulates whether a given principal would be allowed an action before a policy change is applied in production.
Agent Scoping
Narrows the permissions granted to AI agents and workloads so they stop inheriting broad human access.
Related Agents
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
OneCLI
Stores API keys in a central gateway and injects them into outbound requests at call time, so AI agents can use credent…
NVIDIA SkillSpector
Scan agent skills, plugins, and MCP servers before installing them — detects prompt injection, data exfiltration, malic…
Arcade.dev
Handles agent authorization, tool calling, and governance so agents act on behalf of users. MCP runtime with Python/JS…