ClawHub
Back to skill

Security audit

Datawhale Learning Navigator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed learning navigator that searches a bundled catalog and links to external tutorial sources without hidden persistence or privileged behavior.

Install if you want a navigator for Datawhale's mostly Chinese learning materials. Expect it to run a local Python search helper and, when available, open external tutorial links for verification; review linked third-party licenses before redistributing lesson material.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The code only tokenizes a user query, reads a local file at references/source-catalog.md, scores catalog lines, and prints up to 12 matching entries. This supports a narrow source-finding capability, which is only a small subset of the declared description ('find original lessons'). The broader declared purpose emphasizes AI-native software delivery lifecycle functions such as diagnosing gaps, building plans, and designing governed delivery workflows; none of those behaviors are present. Resource access is also narrower than implied: it uses only a bundled local catalog and explicitly performs no network access. Therefore the description materially overstates and misrepresents the code’s actual primary behavior.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
4. Open only the top matching links from [references/source-catalog.md](references/source-catalog.md) using the available browser or HTTP tool.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The routing table instructs users to search Chinese terms such as 产品, 前端, and 部署 even though many learner signals are written in English. This creates an implicit language/locale constraint in the skill behavior without telling users they may need Chinese queries or offering a language alternative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations in natural-language content. This markdown file consistently presents the catalog as Chinese-only, including the heading, descriptions, and section labels, but does not indicate that Chinese is optional, configurable, or required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The fallback message tells users to try a broader Chinese or English concept name, while the matching logic and bundled domain terms are partially language-specific. This creates a mild language/locale bias without an explicit user opt-in or clear documentation that the catalog is bilingual or Chinese-focused.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.