Back to skill

Security audit

融资融券

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Cue research helper, but it tells the agent to fetch and run mutable external code that can use a local Cue API key.

Install only if you are comfortable letting the skill download or update the Cue runner and run it locally with access to your Cue API key and credits. Prefer reviewing or pinning the runner version before use, and confirm the credit-spending prompt 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The '何时用' section says only '融资融券:行情与交易', which is a very broad domain label rather than a specific trigger scope. It does not clarify what kinds of requests should activate this skill versus ordinary market/trading discussion, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to clone or update a remote repository and then use code from that repository as part of execution. This expands the trust boundary from a static skill file to mutable third-party code, creating a supply-chain risk where the fetched repository could change over time, be compromised, or contain unsafe behavior unrelated to the stated research task.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill directs use of a locally stored API key from ~/.cue/config.json, encouraging the agent to rely on sensitive credentials present on the host. Skills should not instruct agents to discover or consume local secrets from filesystem locations, because this can normalize secret access and lead to unintended credential exposure or misuse during execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language description and operating instructions are fully Chinese and do not indicate that the user can choose another language. Under the policy, forcing a specific language without opt-in is a locale/language policy concern unless the constraint is explicitly justified as region-specific.

Content

No source excerpt is available for this finding.