Security audit

Feed To Md Tool Free

Security checks across malware telemetry and agentic risk

Overview

The skill is mainly an RSS-to-Markdown helper, but its activation wording is much broader than that while it can fetch URLs and write files.

Install only if you want an agent to fetch RSS/Atom feeds and save converted Markdown locally. Use it for explicit feed-conversion requests, avoid letting it activate for unrelated document or search tasks, and review any generated command, URL, and output path before execution.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

High

Confidence: 94% confidence
Finding: The trigger keywords are extremely broad, covering common tasks like file processing, document conversion, search, and retrieval. In an agent environment, this can cause the skill to activate for unrelated requests and then use its remote-fetch and local-write capabilities in contexts the user did not intend, increasing the risk of prompt hijacking, SSRF-style URL fetching, or unauthorized filesystem changes.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill materially interacts with external networks and the local filesystem, but the description does not clearly warn about those side effects. In agent settings, hidden fetch-and-write behavior reduces informed consent and makes it easier for a benign-looking conversion task to be abused to retrieve attacker-controlled content and persist it locally.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.