Content Recycler

Security checks across malware telemetry and agentic risk

Overview

This skill locally turns user-provided content into social media drafts, and the file reads/writes are disclosed and purpose-aligned.

Review generated posts before publishing or scheduling them, avoid feeding confidential material unless you intend to repurpose it, and keep outputs in a folder you control. If using the optional cron or social scheduling examples, configure them yourself and confirm no draft is posted without review.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 81% confidence
Finding: The skill documentation instructs users to run local scripts that read input files and write generated output, but the skill declares no permissions. This mismatch is a real security issue because it hides file-system capabilities from whatever permission or review model governs skills, reducing transparency and making it easier for downstream automation to perform unexpected reads or writes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal