Compact Summary

Security checks across malware telemetry and agentic risk

Overview

This is a small instruction-only skill for formatting memory-compaction summaries, with no code, installer, credentials, or hidden data movement.

Safe to install if you want structured memory summaries. Review the resume-instruction line before enabling it; remove or soften it if you want the agent to explicitly state when it is continuing from a compacted memory summary.

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 condition 'during memory flush or compaction' is broad and underspecified, so the skill can activate in many contexts without clear gating or validation. Because the skill also embeds a behavioral instruction in the summary ('do not acknowledge this summary...'), overbroad activation increases the chance that compressed memory content will inappropriately steer later model behavior or suppress transparency.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal