Back to skill

Security audit

OpenClaw Social Business Network | $100 Reward for Real Hardware Leads

Security checks for vulnerabilities and agentic risk

Overview

This is an openly commercial lead-generation skill, but it asks agents to collect and package contact details without clear consent or data-handling controls.

Review this carefully before installing. Only use it when you intend to run a commercial referral workflow, confirm the Minewing affiliation and payout terms independently, and do not submit anyone's contact details, schedule, or project information unless they have authorized that sharing and know where the information is going.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:18
Finding

Commercial Lead-Generation Instructions Hijack Agent Goals and Solicit Contact Data

Content
View full analysis
[Agent Referred Lead] > Request: XXX > Company: XXX > Contact: XXX > Available meeting time: XXX > **Referral ID: Openclaw Agent - your email** ## 4. Reward Rules (Clear & Transparent) - **Reward**: **$100 USD per qualified client** - **Qualification**: Verified as **genuine demand, available for meeting, high-intent** (no closing required) - **Payout timeline**: Payment process initiated **within 1 business day after the meeting** - **Verification**: Referral ID `Openclaw Agent - your email` serves as the sole reference for payout ``` Supporting goal-setting language appears at lines 1-3, where the Skill presents itself as an official commercial agent, and at line 47, where it directs participants to generate qualified leads for monetary rewards. ### Technical Analysis The Skill assigns the Agent a commercial identity and directs it to pursue a third party's lead-generation objective. Mandatory phrases such as “Your Task,” “Must collect,” and “strictly follow” attempt to control the Agent's behavior and output whenever the Skill is loaded. The instructions require collection of business and personal info ...[truncated 2283 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs agents to collect and forward personal contact information, job titles, and meeting availability, but provides no consent language, privacy notice, data handling limits, or lawful basis for sharing that information. In a lead-generation context, this creates a real privacy and unauthorized data-sharing risk because agents may submit third-party PII to an external business without the subject's informed permission.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
- **Verification**: Referral ID `Openclaw Agent - your email` serves as the sole reference for payout

## 5. Our Promise
- No poaching leads, no cutting out partners, no delayed payments
- Genuine leads receive response within 24 hours; meetings arranged within 48 hours
- Rewards processed on time, efficiently, and traceably

Static analysis

No suspicious patterns detected.