T08 · Insecure Dependencies
Warning
- Location
SKILL.md:8- Finding
Unpinned Third-Party Dependencies and Ambiguous npx Package Resolution
- Content
View full analysis
- Remediation
View remediation
Security audit
Gemini Nano Banana
Security checks for vulnerabilities and agentic risk
Overview
The skill appears purpose-aligned for Gemini image generation, but it needs review because it uses an API key with unpinned gateway dependencies and documents extra image-analysis capabilities outside the main tool list.
Review before installing. Use a dedicated, revocable OneKey API key, avoid privileged/global installs where possible, pin dependency versions, and only send images or prompts you are comfortable routing through the OneKey/Gemini provider path.
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)
Vulnerability Patterns
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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
Findings (5)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
The skill exposes sensitive capabilities through environment variable access and file-reading behavior but does not declare any explicit tool scope such as permissions or allowed-tools. This weakens containment and reviewability because operators cannot easily determine or enforce what the skill is permitted to access, increasing the chance of unintended secret exposure or overbroad execution in agent runtimes.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The manifest presents the skill as a generic Gemini image-generation gateway, but the documented usage includes OCR and image item-listing functions not clearly declared in the manifest’s tool descriptions. This capability mismatch can mislead reviewers and users about the true data-processing scope, especially where images may contain sensitive text or personal information.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 93% confidence
- Finding
The documentation instructs users to run the skill through
npx onekeywithout pinning a specific package version. This creates a supply-chain risk because a future compromised or incompatible package release could be fetched and executed implicitly at runtime.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 93% confidence
- Finding
This is a second instance of unpinned
npx onekeyexecution guidance, carrying the same supply-chain exposure as the earlier example. Repeated unsafe examples increase the likelihood that users will adopt insecure installation and execution practices.- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The skill allows writing generated images to user-specified relative or absolute paths but does not prominently warn about file-write behavior or path safety expectations. In agent environments, this can lead to accidental overwrites, writes to sensitive directories, or misuse when unsafe path input is passed through automation.
- Content