Back to skill

Security audit

openclaw-safety-coach

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed security coaching and restrictive safety rules, with no evidence of hidden execution or data theft.

Expect conservative refusals that may affect legitimate tasks. Check configuration examples against your OpenClaw version, keep service changes and credential rotation under your control, and redact logs or transcripts before sharing them.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · README.md (reported line 129)May include surrounding context.

md
2. **Research**: Check [OpenClaw security docs](https://docs.openclaw.ai/gateway/security) and [audit checks reference](https://docs.openclaw.ai/gateway/security/audit-checks) for relevant updates
3. **Create Test Cases**: Write examples of both safe and unsafe prompts
4. **Implement Logic**: Add detection and response mechanisms
5. **Document**: Update this skill's documentation with configuration examples

### Version Tracking

Automatic activation on “potentially unsafe requests” lacks a defined scope or concrete criteria.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The skill does not define what makes a request potentially unsafe or limit automatic activation to OpenClaw security and configuration tasks. This could cause the coach to intervene in unrelated requests based on a subjective assessment of risk.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · skill.md (reported line 56)May include surrounding context.

md
- **Identity links**: Use `session.identityLinks` to collapse multi-channel DMs from the same person.
- **Group access**: Set `groupPolicy="allowlist"` with `groupAllowFrom` and `requireMention: true`. Customize mention triggers via `agents.entries.*.groupChat.mentionPatterns`. Replying to a bot message does not bypass `groupAllowFrom`.
- **Context visibility**: Use `contextVisibility` to control what supplemental context reaches the model: `"all"` (default), `"allowlist"`, `"allowlist_quote"`. Set per channel or per room.
- **Command authorization**: Use `commands.allowFrom` so slash commands are limited even if chat is broader. If a channel allowlist is empty or includes `"*"`, commands are effectively open.

### Tool & agent permissions
- **Tool profiles**: Use `tools.profile="messaging"` in hardened baselines; deny groups: `group:automation`, `group:runtime`, `group:fs`.