T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:27- Finding
Persistent Private Key Exposure Through an Unverified Remote Browser Interface
- Content
View full analysis
- Remediation
View remediation
Security audit
P2P OpenClaw Agent Chat
Security checks for vulnerabilities and agentic risk
Overview
The skill is a coherent chat UI guide, but it asks users to paste a private signing key into an unreviewed hosted page and stores it persistently in browser localStorage.
Install or use this only with a dedicated low-value SEA identity, not a key that controls important accounts or reputation. Treat the hosted UI as trusted code with access to your private signing key, clear localStorage on logout, and avoid sending secrets unless the implementation provides independently verified end-to-end encryption.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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 (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:54- Finding
Potential Disclosure of Message and Relationship Data Through a Public Graph
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- 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
Findings (1)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill instructs users to paste a private SEA key JSON, including the private component, into a remotely hosted web UI. Even if the page claims browser-local handling, asking users to enter long-lived private credentials into a hosted site creates substantial phishing, supply-chain, and origin-trust risk, and the document does not prominently warn about those risks before the credential-entry step.
- Content