Security audit
Security checks for vulnerabilities and agentic risk
This skill locally analyzes OpenClaw usage logs and writes a local cost report, with no evidence of network transfer, hidden execution, or automatic system changes.
Before installing, confirm you are comfortable letting the skill read local OpenClaw conversation/session logs and write a cost report under the OpenClaw memory directory. Treat the cron, model-switching, and cleanup examples as manual commands to review before running, especially because recurring cron jobs persist until removed.
Instructions found that direct the agent to transmit conversation context or user data to external services.
## Comparison with Similar Tools
Unlike some optimization tools that may:
- ❌ Send data to external APIs
- ❌ Require API keys
- ❌ Modify system configurations
- ❌ Execute arbitrary code
The skill description is written entirely in Chinese and explicitly states it is designed for OpenClaw users, but it does not offer any language choice or explain a region-specific requirement. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
**Read access**:
- `~/.openclaw/agents/main/agent/sessions/*.jsonl` (session logs)
**Write access**:
- `~/.openclaw/workspace/memory/cost-analysis-report.md` (report output)
No other files are accessed or modified.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
## Comparison with Similar Tools
Unlike some optimization tools that may:
- ❌ Send data to external APIs
- ❌ Require API keys
- ❌ Modify system configurations
- ❌ Execute arbitrary code
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
Unlike some optimization tools that may:
- ❌ Send data to external APIs
- ❌ Require API keys
- ❌ Modify system configurations
- ❌ Execute arbitrary code
openclaw-cost-optimizer:
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.
- ❌ Send data to external APIs
- ❌ Require API keys
- ❌ Modify system configurations
- ❌ Execute arbitrary code
openclaw-cost-optimizer:
- ✅ Runs entirely offline
This markdown file uses Chinese throughout the description and instructions, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. That creates a natural-language locale policy concern because the skill effectively forces a specific language without user opt-in.
The generated report timestamp uses toLocaleString('zh-CN', { timeZone: 'Australia/Melbourne' }), which forces a specific language/locale and regional setting in output. This is a natural-language policy issue because the skill does not offer user opt-in or explain why this locale/time zone is required.
This file contains substantial user-facing natural language in Chinese alongside English feature labels, but it does not indicate that the skill is intentionally region-specific or offer any language/locale choice. Under the policy rule for natural-language constraints, forcing or assuming a language without opt-in can be a policy concern.
The package description is written entirely in Chinese and provides no indication that users can choose another language or that the skill is intended only for a Chinese-speaking or region-specific audience. This creates a natural-language locale constraint that is not documented as optional or justified.
No suspicious patterns detected.