Use this skill when you need to audit OpenClaw AI agent configurations for security risks. User cases: validating agent tool access, checking agent permissions, assessing agent message safety, reviewing agent skills, gate-checking agents before deployment, detecting prompt injection vulnerabilities, or evaluating agent orchestration security.
Audit AI agent configurations for security risks via Cybercentry ACP. Returns Critical/High/Medium/Low risk level.
acp setup (one-time only)acp browse "Cybercentry" to find the provider walletacp job create <wallet> openclaw-ai-agent-verification --requirements '{"tool": {...}, "config": {...}}'acp job status <jobId> until COMPLETED| Parameter | Type | Required | Description |
|---|---|---|---|
tool | Object |
| No |
Tool to validate (contains name and args) |
tool.name | String | Yes | Tool name |
tool.args | Object | Yes | Tool arguments |
config | Object | Yes | Configuration (filename: openclaw.json or JSON content) |
skills | String | No | Skills content (filename: SKILL.md or JSON content) |
message | String | No | Message to validate |
sessionId | String | No | Session identifier for tracking conversation context |
| Field | Type | Format | Description |
|---|---|---|---|
report | String | Plain | Security risk report |
config is required - pass the openclaw.json content or an empty object {}tool.args must be an object, even if empty - use {} not null