ClawHub
Back to skill

Security audit

cpef-psbc

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Review item because it describes enterprise banking balance access and payment approval without clear authorization or confirmation safeguards.

Install only for a controlled PSBC enterprise banking workflow. Before enabling payment operations, require explicit user confirmation, verify bank-side authorization and approval flow, restrict credentials and account access to least privilege, and treat the placeholder config as incomplete until reviewed by someone responsible for the banking integration.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly supports banking operations including balance inquiry, transaction detail retrieval, and payment approval, but the description provides no warnings, safeguards, or usage constraints for actions that can expose sensitive financial data or move funds. In this context, omission of safety guidance materially increases the risk of unauthorized or accidental account access and payment execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The natural-language description and parameter annotations are entirely in Chinese, with no indication that the skill is region-specific or that users may choose another language. Per the policy, forcing a specific language without opt-in can be a locale-policy violation unless the constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.