T06 · System Persistence
Error
- Location
SKILL.md:257- Finding
Recurring Autonomous Agent Turns Installed Through OpenClaw Scheduler
- Content
View full analysis
- Remediation
View remediation
Security audit
OpenClaw Money Maker
Security checks for vulnerabilities and agentic risk
Overview
This skill is a money-making guide, but it asks users to create persistent autonomous agent tasks and store multiple platform credentials in plaintext without enough control or safety guidance.
Review this carefully before installing. Do not add the scheduler or HEARTBEAT entries unless you explicitly want recurring autonomous activity, and require manual approval before any claim, submission, or public post. Store credentials in a keychain or secret manager instead of the suggested plaintext JSON file, use scoped revocable tokens, and avoid saving reusable passwords.
Vulnerability Patterns
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
- 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
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (3)
T02 · Agent Memory Poisoning
Error
- Location
SKILL.md:273- Finding
Persistent Commercial Instructions Written Into Agent Heartbeat State
- Content
View full analysis
- Remediation
View remediation
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:42- Finding
Multiple Reusable Credentials Stored Together in Plaintext JSON
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Rogue AgentSelf-Modification, Session Persistence
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 96% confidence
- Finding
The skill explicitly centralizes sensitive credentials, including an API key and plaintext password, in a predictable file path. This creates a high-value target for local malware, accidental disclosure, or other skills/processes that can read files, and the inclusion of a reusable account password raises the blast radius beyond a single API token.
- Content
Step 2: Save Your Credentials
Create
~/.config/openclaw-earnings/credentials.json:json {
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 78% confidence
- Finding
The skill includes commands that transmit agent-identifying data and capabilities to third-party services. Although registration itself is expected in context, the skill provides direct network calls to external domains without any trust boundary warning, privacy notice, or verification guidance, which can expose metadata or normalize sending data to unvetted services.
- Content
bash # PayAClaw - Task platform curl -X POST https://payaclaw.com/api/agents/register \ -H "Content-Type: application/json" \ -d '{"agent_name":"YourAgentName","description":"Your capabilities","capabilities":["coding","writing"]}'
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill instructs users to store API keys and a plaintext password in a local JSON file without any warning about file permissions, encryption, or secret-management practices. This increases the chance of credential theft via local compromise, backups, logs, or accidental sharing of the config directory.
- Content
Session Persistence
Medium
- Category
- Rogue Agent
- Confidence
- 90% confidence
- Finding
Persisting long-lived session material and credentials in a stable config file enables durable unauthorized access if the host is compromised or the file is copied into backups, repos, or support bundles. In this skill's context, persistent credentials support automated monetization workflows, making silent long-term misuse more likely.
- Content
Step 2: Save Your Credentials
Create
~/.config/openclaw-earnings/credentials.json:json {
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The automation section encourages recurring autonomous checks and posting-related behavior against external platforms without warning about rate limits, unintended actions, account bans, or financial/accountability consequences. In a money-making skill, unattended activity can trigger spam, abuse detections, or actions the user did not intend to authorize continuously.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 75% confidence
- Finding
The file presents earnings information in an otherwise English document using Chinese text for the unit description, without indicating that multilingual output is optional or user-selected. This can conflict with a language or locale policy when the skill implicitly forces a language choice without opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
The skill includes Chinese-language scoring labels in the middle of English instructions and does not explain that this locale choice is intentional or user-selected. That creates a natural-language locale inconsistency that should either be justified or made optional.
- Content
Static analysis
No suspicious patterns detected.