Daily Digest

Security checks across malware telemetry and agentic risk

Overview

This skill locally reads Markdown files in a chosen folder to produce a digest, with no hidden network, credential, persistence, or destructive behavior found.

Install only if you are comfortable with the agent reading Markdown files in the current or specified folder and showing filenames, titles, headings, word counts, and read errors in the digest. For sensitive workspaces, run it on an explicit limited directory rather than the project root.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (2)

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The trigger phrases are broad enough to overlap with ordinary document-assistance requests, increasing the chance the skill activates when a user did not intend a bulk directory scan. In this skill's context, mistaken activation can expose filenames, titles, section headings, and counts from all markdown files in scope.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The description omits a clear privacy warning that the skill scans all .md files in the current or specified directory and includes document names, headings, and counts in its output. Even without reading full contents verbatim, this metadata can reveal sensitive project names, meeting topics, or internal structure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal