Back to skill

Security audit

openclaw configure backup

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local backup helper for OpenClaw config files, with no evidence of hidden execution, exfiltration, or persistence beyond creating backup copies.

Install only if you want a local helper that copies OpenClaw JSON5 config files into timestamped backups. Use it with an explicit openclaw.json path and a backup directory you control, because copied config files may contain sensitive settings.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill describes file read and file write behavior but does not declare any tool scope or allowed-tools restrictions. In agent environments, missing scope declarations can allow the skill to be invoked with broader filesystem capabilities than users expect, increasing the chance of unintended access or modification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description says to use the skill when the user asks to 'backup, create backup of, or save OpenClaw config,' which is broad enough to match ambiguous requests. Over-broad trigger wording can cause unintended invocation and filesystem writes when the user meant something else, especially in automated skill-routing systems.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill metadata says it is for backing up the OpenClaw configuration file, but the CLI accepts any user-supplied path and only checks whether it parses as JSON5. In an agent context, this broadens the tool from a narrowly scoped config backup into a generic file-copy primitive for arbitrary JSON/JSON5-like files, which can expose or duplicate sensitive data outside the intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The example output includes the status message "已备份" in Chinese, but the surrounding documentation is in English and does not state that the skill is region-specific or that the user can choose the language. This suggests a fixed locale behavior without opt-in, which conflicts with the language/locale policy described for this review.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code file contains user-facing and instructional natural language primarily in Chinese, including comments and command-line help strings, with no indication that the tool is region-specific or that users may opt into another language. Under the policy rule for language/locale constraints, forcing a specific language without opt-in is a natural-language policy issue.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The command description says "Validate JSON5 and backup with hash check," while the manifest frames the skill as backing up the OpenClaw config with hash-based change detection. The implementation adds a gating validation step that contradicts the simpler backup intent by refusing to back up files that fail JSON5 parsing, which is not reflected in the stated skill purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.