ClawHub
Back to skill

Security audit

PKU Info Spider

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small documentation-only helper, but it normalizes WeChat scraping with stored session artifacts and anti-crawler bypass guidance without enough scoping or warnings.

Review this carefully before installing or using it. It appears to be documentation-only, but it is meant to support authenticated WeChat scraping and anti-crawler evasion. Only use it for accounts and content you are authorized to access, protect any session files like credentials, and consider adding explicit limits and compliance warnings before publication.

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
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description contains very broad activation triggers, including generic terms like WeChat, article scraping, QR login flow, and API references, which can cause the agent to invoke this skill in contexts broader than intended. Because the skill concerns scraping, session handling, and anti-crawler behavior, over-invocation increases the chance of inappropriate guidance, unintended data exposure, or assistance with risky automation workflows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill documents that it stores token, fingerprint, and bizuin session data under a user config directory, but it does not warn that these are sensitive authentication artifacts. Without an explicit warning, users may mishandle, commit, share, or inadequately protect this material, enabling session theft or unauthorized account access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly describes behavior intended to mimic real users and bypass platform risk controls, but it omits a warning about account suspension, ToS violations, legal/compliance exposure, or operational risk. In this context, the omission is more dangerous because the skill is for scraping a third-party platform and frames anti-crawler evasion as a normal development feature.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The document states that all user-facing strings are in Chinese, which imposes a specific language choice without indicating any user selection, fallback, or opt-in. This is a natural-language policy concern because it forces a locale/language constraint on all users rather than offering a choice or clearly documenting a justified regional limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.