ClawHub
Back to skill

Security audit

elm

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Ele.me cart-building assistant that uses the user's own logged-in session only with consent and stops before payment.

Before installing, understand that this skill can operate inside your already logged-in Ele.me session to inspect address, coupon, and cart information and modify the cart. Review the cart, address, coupon selection, and total yourself before paying; do not share login codes or passwords in chat.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file mixes English headings with Chinese-only release-theme content, which effectively imposes a specific language on readers without any stated opt-in or justification. The policy only calls for natural-language violations, and this is a clear locale/language constraint visible in the document text.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The package description specifies the skill behavior only in Chinese, which can amount to a language/locale policy issue when no user opt-in or documented regional constraint is provided. This may exclude users expecting language-neutral or selectable localization.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.