Security audit

睡后收入系统 V1（OpenClaw版）

Security checks for vulnerabilities and agentic risk

Overview

This skill is an income-automation workflow, but it tells agents to scan local workspaces and publish assets externally without clear review or secret-protection steps.

Install only if you are comfortable with an agent helping automate WeChat drafts and marketplace publication. Before using it, keep AppSecret values in a secure secret store, restrict any workspace scan to an explicit allowlist, exclude secrets and private files, review the full package manifest, and approve each upload or account-impacting action manually.

A.I.G

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)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:24
Finding: Unbounded Workspace Collection and External Publication
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill describes automated public-account draft publishing and states that AppID/AppSecret credentials are prerequisites, but does not warn about the sensitivity of those credentials or the consequences of automated account actions. This can lead users to expose secrets insecurely or authorize unintended publishing activity that affects a real external account.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly describes scanning the workspace, packaging prior work, and publishing it to a marketplace for passive discovery, but provides no requirement for user review, scoping, or redaction before upload. In a real agent environment, this creates a substantial risk of exfiltrating sensitive local files, credentials, proprietary content, or personal data through overbroad collection and publication.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 96% confidence
Finding: All user-facing instructions in this file are in Chinese, and the skill does not indicate that Chinese is an optional or region-specific mode. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.