Back to skill

Security audit

Alibabacloud Aisc Skill Inspection

Security checks for vulnerabilities and agentic risk

Overview

This security-scanning skill is mostly purpose-aligned, but it needs review because it uses cloud credentials and can return hardcoded mock scan results for certain inputs instead of always calling the scanner.

Install only if you are comfortable giving the agent access to Alibaba Cloud credentials with aisc:CreateSkillFileCheck and aisc:ListSubTasks, sending Skill download URLs to Alibaba Cloud AISC, and writing a local scan report. For real security decisions, avoid relying on the documented mock/evaluation sample inputs as proof of a live scan, and prefer pinned dependency versions or a reviewed lockfile.

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill exercises environment, file-write, and network capabilities but does not declare permissions. This creates a transparency and governance gap: a caller or platform may not realize the skill can make outbound API requests and write local reports, which increases the chance of unsafe execution in a broader agent environment.

Unpinned Dependencies

Low
Category
Supply Chain
Content
alibabacloud_aisc20260101>=1.1.0
alibabacloud_credentials>=1.0.0
alibabacloud_tea_openapi>=0.4.0
Confidence
92% confidence
Finding
The dependency is specified with a lower-bound version only, which allows installation of any newer release. This creates supply-chain risk because future incompatible or compromised versions could be pulled into builds without review, reducing reproducibility and making security posture dependent on upstream changes.

Unpinned Dependencies

Low
Category
Supply Chain
Content
alibabacloud_aisc20260101>=1.1.0
alibabacloud_credentials>=1.0.0
alibabacloud_tea_openapi>=0.4.0
Confidence
92% confidence
Finding
Using a non-pinned version range for credentials-related libraries permits unreviewed upstream releases to be installed. If a malicious or vulnerable version is published, environments may consume it automatically, increasing supply-chain exposure and hindering reproducible deployments.

Unpinned Dependencies

Low
Category
Supply Chain
Content
alibabacloud_aisc20260101>=1.1.0
alibabacloud_credentials>=1.0.0
alibabacloud_tea_openapi>=0.4.0
Confidence
92% confidence
Finding
This package is also unpinned and may resolve to different versions over time, which can introduce unexpected vulnerabilities or behavior changes. In a security-scanning skill, dependency trust is especially relevant because the tool may process sensitive scan inputs and credentials for cloud APIs.

Static analysis

No suspicious patterns detected.