Security audit

Manus

Security checks across malware telemetry and agentic risk

Overview

This looks like a real Manus integration, but it needs user review because it can send task data to an external agent service, download generated files, and create shareable result links.

Install only if you are comfortable sending prompts, task details, and generated results to Manus. Avoid using it with secrets, regulated data, or proprietary content unless your organization has approved Manus for that use, and disable or avoid shareable links for sensitive tasks.

SkillSpector

By NVIDIA

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 (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill demonstrates shell-based network operations via curl but declares no corresponding permissions or capability boundaries. This creates a transparency and governance gap: users or the host platform may not realize the skill can invoke shell commands and make outbound requests to external services.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The README states that output files are downloaded locally and delivered directly, but it does not warn users about filesystem side effects, storage location, or the risk of writing untrusted generated content to disk. In an agent skill that fetches externally produced files, this can surprise users and increase exposure to unsafe files or accidental overwrites.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The README describes sending prompts and tasks to Manus but does not clearly warn that user prompts, task data, and possibly related content are transmitted to a third-party external service. This is a privacy and data-handling issue because users may disclose sensitive information without understanding that it leaves the local environment.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The workflow tells operators to download generated files locally and re-send them to users, but provides no safety guidance for handling untrusted or sensitive output. Because Manus is an autonomous agent that can produce arbitrary files, this can lead to unsafe local writes, inadvertent retention of sensitive data, or redistribution of malicious content.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill recommends setting createShareableLink: true but does not warn that this may expose task artifacts or results through externally accessible URLs. If tasks include proprietary, personal, or regulated data, share links can expand access beyond the intended recipient and create a data leakage path.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.