Text Summarizer

Security checks across malware telemetry and agentic risk

Overview

This appears to be a straightforward local text summarizer, with a caution that broad trigger phrases and file inputs can involve sensitive text if used carelessly.

Safe to install for local summarization. Treat any pasted text or file path as sensitive because selected source sentences may be printed in the output, and review summaries against the original when accuracy matters because extractive summaries can still omit context.

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: 84% confidence
Finding: The invocation language is extremely broad (`summarize this`, `TL;DR`, `key points`, `condense`) and overlaps with common user requests, which can cause the skill to trigger on arbitrary text-processing tasks without clear user intent. In an agent environment, that increases the chance of accidental invocation on sensitive documents, emails, or pasted content the user did not explicitly intend to hand to this skill.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal