ClawHub
Back to skill

Security audit

Elective

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PKU course-selection helper, with expected but sensitive login, session, CAPTCHA, and auto-enrollment behavior.

Install only if you intend to let an agent help operate the PKU elective CLI. Before using auto-login, CAPTCHA OCR, or auto-enrollment, confirm which account credentials, session files, and CAPTCHA backend are configured, and prefer manual CAPTCHA handling if you do not want challenge images sent to external recognition services.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
# Check session status
info-auth check

# Auto-login (reads credentials from OS keyring, no password needed)
elective login -p                  # single degree
elective login -p --dual major     # dual degree - major
elective login -p --dual minor     # dual degree - minor

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly documents sending CAPTCHA images to third-party OCR services but does not warn users that challenge data will be transmitted off-platform or describe any privacy, retention, or trust implications. In a university SSO/course-selection context, even CAPTCHA-related traffic can reveal service usage patterns and may expose session-linked data to unvetted external providers.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The line explicitly says all user-facing strings are in Chinese, which is a language policy constraint. There is no indication of user choice, opt-in, or justification that the skill is intentionally limited to a Chinese-only audience.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.