Back to skill

Security audit

huawei-cloud-agentorchard-find-skills

Security checks for vulnerabilities and agentic risk

Overview

This skill searches Huawei Cloud’s public skill catalog without sending search terms, accessing credentials, or automatically installing skills.

Expect Huawei-specific results even for generic skill-finding requests. Search terms are processed locally, and subscribing requires your action on Huawei’s website. Review suggested skills separately; their contents and the live service were outside this artifact review.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
60% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/cli-installation-guide.md (reported line 25)May include surrounding context.

2. 验证网络连通性

bash
curl -s -o /dev/null -w "%{http_code}" "https://devdata.huaweicloud.com/rest/aiasset/user_system/v1/aihub/contents?content_type=skills&limit=1"

返回 200 表示网络可达。

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
60% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/cli-installation-guide.md (reported line 25)May include surrounding context.

2. 验证网络连通性

bash
curl -s -o /dev/null -w "%{http_code}" "https://devdata.huaweicloud.com/rest/aiasset/user_system/v1/aihub/contents?content_type=skills&limit=1"

返回 200 表示网络可达。

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Generic requests to extend functionality or find a tool can activate the AI Gallery skill without marketplace intent.

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

Generic triggers such as wanting to extend functionality or find a tool can select this specific marketplace integration without clear marketplace intent. The workflow then directs the agent to pass the user's input into an external search, creating a risk of unintended query disclosure and vendor-specific task diversion; the read-only scope limits the likely impact.

Content

No source excerpt is available for this finding.