Back to skill

Security audit

Taobao Review Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Taobao/Tmall review-analysis prompt with ordinary Python dependencies and no bundled executable code or persistence.

Install this only if you are comfortable with a skill that may retrieve public Taobao/Tmall review data and install Python packages. Use it with explicit product URLs or clearly identified products, and consider using a virtual environment because the dependencies are not pinned.

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

T08 · Insecure Dependencies

Warning
Location
SKILL.md:13
Finding

Unpinned Third-Party Python Dependencies

Content
View full analysis
Remediation
View remediation
jieba== ``` 2. Generate and commit a lock file containing all direct and transitive dependencies. 3. Record cryptographic hashes for approved distributions and enforce hash verification during installation, such as with `pip --require-hashes`. 4. Restrict package retrieval to an approved Python package index or an internally controlled package mirror. 5. Review and update pinned dependencies through a controlled process that includes vulnerability scanning, package provenance verification, and regression testing. 6. Perform dependency installation under a non-privileged account in an isolated virtual environment or container. 7. Avoid running package installation as `root` or another privileged system account. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
93% confidence
Finding

The skill describes review fetching and analysis but does not clearly warn users that it may retrieve external data from Taobao/Tmall. This can lead to unexpected outbound requests, user confusion about data provenance, and operation in environments where external access should be explicit and consented to.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger examples are broad and generic, which can cause the skill to activate in contexts the user did not clearly intend, including on arbitrary product-analysis requests. Because this skill implies external retrieval and processing of Taobao/Tmall data, overbroad activation increases the chance of unintended network access, privacy surprises, or confusing the user about what actions will be taken.

Content

No source excerpt is available for this finding.