RSS监控

Security checks across malware telemetry and agentic risk

Overview

This is a simple RSS monitoring skill whose network access is expected for fetching feeds.

Install only if you are comfortable with the agent fetching RSS/Atom URLs you provide. Prefer trusted public feed URLs, avoid localhost or private-network URLs unless intentional, and review any future version that adds background polling, saved history, or broader network access.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill fetches user-supplied or configured external URLs via feedparser.parse(url) without clearly warning that network access will occur. In an agent environment, this can enable unintended requests to attacker-controlled endpoints, creating SSRF-like exposure, privacy leakage, or retrieval from internal-only resources if URL sources are not constrained.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal