
agentsh
Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
ai-securityauthentication-authorizationcloud-security+7
385

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

Zero-trust sandbox for AI agents with kernel-level filesystem jail, transparent network proxy, and YAML-based policy engine to intercept and control…

Documents CVE-2026-52618 with a PoC for OS command injection in @webfer/mcp-ansible-drupal via executeDeployment extraVars, plus detection guidance…