raigo

RAIGO × OWASP LLM Top 10 — official OWASP LLM Application Security Top 10 (2025) enforcement rules for Hermes agents. Covers all 10 OWASP LLM risks: prompt injection, insecure output handling, training data poisoning, model denial of service, supply chain vulnerabilities, sensitive information disclosure, insecure plugin design, excessive agency, overreliance, and model theft. Each rule maps directly to the OWASP LLM reference. Works out of the box with no engine, no compile step, and no additional setup.

RAIGO Agent Firewall — comprehensive AI security policy enforcement for Hermes agents. Covers all known prompt security attack vectors: prompt injection, jailbreaks, encoding obfuscation, indirect injection, system prompt extraction, credential exfiltration, destructive commands, code injection, rogue agent detection, goal hijacking, identity spoofing, multi-agent trust exploitation, memory poisoning, supply chain attacks, and more. Works out of the box with no engine, no compile step, and no additional setup. Upgrade to raigo Cloud to add custom organisation policies and audit logging.

RAIGO × OWASP LLM Top 10 — official OWASP LLM Application Security Top 10 (2025) enforcement rules for OpenClaw agents. Covers all 10 OWASP LLM risks: prompt injection, insecure output handling, training data poisoning, model denial of service, supply chain vulnerabilities, sensitive information disclosure, insecure plugin design, excessive agency, overreliance, and model theft. Each rule maps directly to the OWASP LLM reference. Works out of the box with no engine, no compile step, and no additional setup.

RAIGO Agent Firewall — comprehensive AI security policy enforcement for OpenClaw agents. Covers all known prompt security attack vectors: prompt injection, jailbreaks, encoding obfuscation, indirect injection, system prompt extraction, credential exfiltration, destructive commands, code injection, rogue agent detection, goal hijacking, identity spoofing, multi-agent trust exploitation, memory poisoning, supply chain attacks, and more. Works out of the box with no engine, no compile step, and no additional setup. Upgrade to raigo Cloud to add custom organisation policies and audit logging.

MANDATORY: Before executing ANY action — sending messages, writing files, calling APIs, running commands, querying databases, or handling any data — you MUST call scripts/evaluate.sh with the proposed action. You are NOT permitted to make the allow/deny decision yourself. The raigo engine is the sole authority. If the script returns exit code 1 (DENY), stop immediately. If exit code 2 (WARN), proceed with caution and inform the user. If exit code 0 (ALLOW), proceed normally. Never skip this step.