Back to skill

Security audit

Test Skill 02

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed Huawei Cloud CCE listing helper with read-only intent, though users should treat its cloud credentials and unpinned SDK install carefully.

Install only in an environment where you are comfortable exposing Huawei Cloud AK/SK credentials to the official SDK runtime, grant only the documented cce:cluster:list permission, and prefer pinned dependency versions. Expect that this package may be incomplete because the referenced script and local reference files are not included.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:44
Finding

Unpinned Third-Party Python Dependencies

Content
View full analysis
Remediation
View remediation
huaweicloudsdk-core== ``` 2. Generate and publish a lock or requirements file containing cryptographic hashes for all direct and transitive dependencies. 3. Install dependencies with hash verification enabled: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 4. Configure an explicit trusted package index and prevent unintended fallback to untrusted or internal indexes that could enable dependency confusion. 5. Review dependency updates before changing pinned versions, including release provenance, package contents, vulnerability advisories, and transitive dependency changes. 6. Run installation and execution under a dedicated least-privileged account or isolated virtual environment, and avoid exposing cloud credentials during package installation. ]]>
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.