Back to skill

Security audit

基金投顾

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned, but it asks the agent to fetch and run changing external code that automatically uses a local Cue API key.

Install only if you trust the Cue runner repository and are comfortable with it using your local Cue API key and credits. Prefer reviewing or pinning the runner before first use, and confirm each paid research run carefully.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill’s natural-language description and operating instructions are entirely in Chinese, with no indication that users may interact in another language or select a preferred locale. Under the stated policy, forcing a specific language without user opt-in is a locale-policy violation unless the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to clone or update and then execute code from an external Git repository as part of normal operation. That creates a software supply-chain risk: repository contents can change over time, mirror sources may be compromised, and the fetched code is granted execution on the host without pinning, verification, or sandboxing. In a fund-advisory skill, remote code bootstrapping is not inherently required by the stated business purpose, so the context makes this more suspicious rather than less.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill states that the runner will automatically read an API key from ~/.cue/config.json, which normalizes access to local credentials not clearly scoped in the manifest purpose. Even if intended for convenience, instructing an agent to rely on local secret discovery increases the chance of unauthorized credential use, accidental exfiltration, or use of the user's paid account without informed consent. In this context, the skill already requires external service access and billing, so implicit credential access is especially sensitive.

Content

No source excerpt is available for this finding.