Back to skill

Security audit

商机挖掘

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for Cue business research, but it asks the agent to fetch and run mutable external code that can use a local Cue API key and spend credits.

Install only if you are comfortable letting a Cue runner cloned from sensedeal/cue-skills run locally, read your Cue API key, contact Cue services, and consume credits after confirmation. Prefer reviewing or pinning the runner repository before first use in sensitive environments.

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

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is written to require operation in Chinese for the skill scenario, and the instructions do not offer any language or locale choice to the user. This can violate language/locale policy when a skill implicitly enforces a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The '何时用' section describes the skill as applicable to '商机挖掘:企业尽调、产业链与研报、全网检索', which is a very broad set of common research activities without clear constraints on when the skill should or should not be invoked. It does not provide specific trigger phrases, scope limits, or negative examples to prevent unintended activation for generic company research requests.

Content

No source excerpt is available for this finding.