Back to skill

Security audit

Price Import

Security checks for vulnerabilities and agentic risk

Overview

The skill mainly supports a price-import workflow, but it also includes broader product-catalog changes, persistent requirements-management files, and an insecure hard-coded HTTP import-log link that users should review before installing.

Install only if you are comfortable granting this skill authority to process and upload pricing files, call business APIs, and potentially affect product-catalog data. Prefer requiring matched-only imports, removing or separating the /fix requirements workflow, replacing the HTTP IP link with authenticated HTTPS, and confirming how raw files and import logs are retained and deleted.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:173
Finding

Import Workflow Can Create Products Outside the Declared Least-Privilege Boundary

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:275
Finding

Import Log Interface Is Exposed Through a Hard-Coded Plaintext HTTP URL

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill advertised as a price-import tool also exposes a separate /fix workflow for requirements management and software-change orchestration. This is dangerous because it expands the skill from narrow data import into broader project/file-management behavior, increasing the chance of unauthorized task creation, scope creep, and misuse of the agent to persist or relay development instructions outside the user’s original intent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The documented behavior goes far beyond price import and instructs the agent to generate requirement documents, manage registries, create directories, and coordinate downstream development tasks. This materially increases attack surface because arbitrary user prompts can be transformed into durable workspace artifacts and operational requests, enabling persistence, lateral workflow abuse, or unauthorized change-management actions.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s responsibility boundaries contradict earlier instructions that allow direct creation of new products during import. Contradictory authority rules are dangerous because an agent may choose the more permissive branch and perform higher-impact actions than intended, such as modifying the product catalog when it should only report unmatched items for separate handling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill describes uploading raw source files and extracted pricing data to backend APIs and storing them in import logs/attachments, but does not explicitly warn users before collection and transfer. This is dangerous because users may unknowingly send sensitive business data, customer information, or proprietary pricing sheets to persistent backend storage without informed consent.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
96% confidence
Finding

This duplicate finding points to the same persistent directory-creation behavior for requirements documents under the user workspace. The risk remains that prompt-supplied content can be materialized and retained across sessions, enabling unintended persistence and possible downstream misuse.

Content

Scanner excerpt · SKILL.md (reported line 652)May include surrounding context.

  1. 创建目录(如不存在):

    bash
    mkdir -p ~/.openclaw/workspace/requirements
    
  2. 生成需求文档:

Session Persistence

Medium
Category
Rogue Agent
Confidence
96% confidence
Finding

This duplicate finding points to the same persistent directory-creation behavior for requirements documents under the user workspace. The risk remains that prompt-supplied content can be materialized and retained across sessions, enabling unintended persistence and possible downstream misuse.

Content

Scanner excerpt · SKILL.md (reported line 652)May include surrounding context.

  1. 创建目录(如不存在):

    bash
    mkdir -p ~/.openclaw/workspace/requirements
    
  2. 生成需求文档:

Session Persistence

Medium
Category
Rogue Agent
Confidence
96% confidence
Finding

This duplicate finding points to the same per-system archive directory creation, which is still outside the least-privilege scope of a price-import skill. The persistence is more dangerous here because the skill already includes broad requirements-management behavior, so directory creation supports a wider non-import workflow surface.

Content

Scanner excerpt · SKILL.md (reported line 766)May include surrounding context.

  1. 创建系统目录:

    bash
    mkdir -p ~/.openclaw/workspace/requirements/{SYS}/archive
    
  2. 更新注册表:

Session Persistence

Medium
Category
Rogue Agent
Confidence
96% confidence
Finding

This duplicate finding points to the same per-system archive directory creation, which is still outside the least-privilege scope of a price-import skill. The persistence is more dangerous here because the skill already includes broad requirements-management behavior, so directory creation supports a wider non-import workflow surface.

Content

Scanner excerpt · SKILL.md (reported line 766)May include surrounding context.

  1. 创建系统目录:

    bash
    mkdir -p ~/.openclaw/workspace/requirements/{SYS}/archive
    
  2. 更新注册表:

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The collaboration guidance says unrecognized products should be handed off to another role, but earlier workflow permits the skill to create them directly. This inconsistency can cause the agent to bypass intended separation of duties, making unauthorized catalog mutations more likely during ambiguous conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description is written as a Chinese-only product-facing description, and the document does not indicate that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.