T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:10- Finding
Watchdog Design Requires Excessive Root Privileges
- Content
View full analysis
- Remediation
View remediation
Security audit
OpenClaw Watchdog
Security checks for vulnerabilities and agentic risk
Overview
The skill is purpose-aligned but should be reviewed because it directs a root/systemd watchdog to automatically restart a service without a bundled, auditable implementation or tight controls.
Install only if you expect this skill to run a privileged watchdog that may automatically restart openclaw-gateway. Before use, require an auditable watchdog.sh, explicit confirmation for restart-capable monitoring, strict parameter validation, and narrowly scoped service permissions instead of unrestricted root operation.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
Findings (1)
Vulnerability Patterns
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill description and usage guidance do not prominently warn users that the watchdog can automatically restart a systemd service, which is a material system-state change. In a root/systemd context, missing disclosure is risky because users may invoke the skill without realizing it can disrupt service availability, alter process state, or interfere with troubleshooting and production operations.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger phrase "帮我启动 openclaw-watchdog" is close to ordinary conversational language and does not define clear invocation boundaries, increasing the chance of accidental or context-confused activation. In this skill, unintended invocation is more dangerous than usual because the documented behavior includes monitoring, service checks, and automatic restarts that can change system state on a privileged host.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The custom-port example remains broadly phrased and accepts a free-form parameter without clear trigger scoping, which can cause the skill to activate from normal conversation and apply user-supplied operational settings. Because this skill may monitor arbitrary ports and trigger systemctl restarts, ambiguous activation combined with parameter parsing increases the chance of unintended privileged actions.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill instructions and example notification content are presented only in Chinese, with no indication that the user can choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy concern.
- Content
Static analysis
No suspicious patterns detected.