Security audit
OpenClaw Cost Guard
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrow OpenClaw cost-audit helper that reads a local config and reports budget-risk findings without modifying files or sending data elsewhere.
Install only if you are comfortable with the skill reading the OpenClaw config path you provide, or the default ~/.openclaw/openclaw.json. Review the JSON output before sharing it, since it can reveal model choices, budget settings, and workflow patterns even though the script does not print the full config.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.