Security audit

Alibaba Cloud Compute FC Agentrun

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Alibaba Cloud AgentRun management helper, with expected cloud credential use and resource changes that users should run carefully.

Install only if you intend to manage Alibaba Cloud AgentRun resources. Use least-privilege RAM credentials, verify the endpoint and region, review output JSON before sharing it, and treat the cleanup script as destructive because it deletes the specified runtime endpoint and runtime.

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
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill exposes capabilities that involve reading environment variables and writing files, but it does not declare any explicit tool scope or permission boundaries. This increases the chance that an agent or operator will run the skill with broader access than intended, allowing sensitive credentials from environment variables or filesystem locations to be accessed or persisted without clear authorization controls.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill directs users to supply cloud access key credentials via environment variables without any warning about secret handling, masking, storage, or least-privilege use. In practice, this can cause credential exposure through logs, shell history, evidence files, or overly permissive agent behavior, leading to unauthorized access to the Alibaba Cloud account.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The cleanup workflow instructs deletion of runtime resources by ID, but it does not clearly warn that the action is destructive or recommend confirmation before execution. In a cloud-management skill, this can lead to accidental deletion of active resources, service disruption, or loss of configuration if an agent follows the instructions automatically.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The script deletes an agent runtime endpoint and then the runtime itself, which are destructive operations. Although the docstring mentions deletion, there is no user-facing confirmation prompt or warning immediately before execution to disclose that the resources will be permanently removed.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file is written entirely in Chinese, including the title and descriptive text, without any indication that language selection is optional or that the document is intended only for a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The entire skill documentation is written in Chinese and does not indicate any language choice, opt-in, or region-specific justification. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The file content is entirely in Chinese and presents the documentation heading without offering any language or locale choice. Under the policy, natural-language content that forces a specific language without user opt-in can be a locale-policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This code creates an output directory and writes the full API response to a JSON file, but the user is only informed after the write completes. There is no confirmation prompt, pre-write notice, or explanatory comment/docstring describing that runtime data will be persisted locally.
Content: No source excerpt is available for this finding.