ClawHub
Back to skill

Security audit

hiagent智能体对话

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward hiagent chat connector that sends user IDs, conversation IDs, and prompts to the configured hiagent API as part of its stated purpose.

Install this only if you trust the configured hiagent endpoint and are comfortable sending prompts, user identifiers, and conversation metadata to that service. Prefer an HTTPS HIAGENT_API_URL, a least-privilege API key, and avoid entering sensitive prompts unless the service's retention and access controls are acceptable.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs sending persistent user identifiers, conversation IDs, and user queries to an external hiagent service, but it does not warn users that their prompts and conversation history will leave the local agent context. This creates a real privacy and data-handling risk because sensitive prompts, identifiers, and prior chat history may be transmitted or retrieved without informed consent or minimization.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This command sends a user identifier to an external endpoint using credentials from environment variables, which is an external data transmission path. In the context of a chat skill, such transmission may be functionally necessary, but it is still security-relevant because it exposes user-linked metadata to a third-party service and can enable enumeration or privacy leakage if used without user awareness and endpoint validation.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

use get_conversation_list api to get conversation history list

bash
curl --location '$HIAGENT_API_URL/get_conversation_list'
--header 'Apikey: $HIAGENT_API_KEY'
--header 'Content-Type: application/json'
--data '{

Static analysis

No suspicious patterns detected.