Back to skill

Security audit

10jqka Concept

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese A-share concept lookup tool that contacts disclosed public stock-data sites and uses a local cache, with no evidence of deception, credential access, command hijacking, or destructive behavior.

Install in a dedicated Python environment, review or pin dependency versions, and be aware that stock codes/concept names are sent to Tonghuashun/iWencai services. The batch script creates a local cache under ~/.openclaw/workspace/memory/cache that users may want to clear or restrict if working in a shared environment.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:153
Finding

Unpinned Python Dependencies Allow Supply-Chain Drift

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/query_concepts_batch.py:19
Finding

Predictable Persistent Cache Permits Symlink Following and Cache Poisoning

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill includes code and instructions that perform outbound network access and imply code execution, but the manifest does not declare any explicit tool scope or permissions. This creates a governance gap: an agent/runtime may permit broader capabilities than reviewers or users expect, increasing the risk of unintended network use, data exfiltration, or future expansion to file operations without clear authorization.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language content of the skill, including its description, usage, examples, and cautions, is presented only in Chinese. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation unless the restriction is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest and module documentation describe this skill as querying a stock's concept sectors by scraping the Tonghuashun F10 page. However, this function adds a separate capability to query a concept board and enumerate its component stocks, which is a broader behavior than the stated stock-concept lookup purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The request header sets "Accept-Language" to prefer "zh-CN", which imposes a specific language/locale behavior in the skill. Under the policy, locale constraints should be user-selectable or clearly justified as region-specific; this file contains neither.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This code persists stock query results under ~/.openclaw/workspace/memory/cache and later writes JSON data there via save_cache. Although the code has internal comments/docstrings, it does not provide a clear user-facing disclosure at runtime that local files will be created and updated.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script sends stock codes to iwencai.com and also queries 10jqka.com.cn, which transmits user-provided or system-derived data to external services. While this behavior is part of the script's function, the file lacks a clear disclosure in usage/help text or top-level documentation that external HTTP requests will occur.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

When preset data is unavailable or the first query path fails, the script automatically fetches data from basic.10jqka.com.cn. There is no runtime notice or help text informing users that external web scraping requests will be made as part of execution.

Content

No source excerpt is available for this finding.