Briefing-pro

Security checks across malware telemetry and agentic risk

Overview

This skill coherently turns user-provided text, URLs, or files into one-page briefing slides, with expected document parsing and webpage fetching disclosed.

Install if you want a briefing generator that may fetch supplied URLs and read uploaded files to create slide-style output. Avoid using it for sensitive documents unless you are comfortable with that content being parsed and rendered, and consider narrowing the generic “摘要” trigger to reduce accidental activation.

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 (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger conditions include very broad everyday terms such as “摘要”, which can match many unrelated user requests and cause unintended activation of this skill. Because the skill fetches URLs, parses uploaded files, and generates outputs automatically, accidental invocation could expose user content to unnecessary processing or lead the agent down the wrong workflow.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal