Summarize File

Security checks across malware telemetry and agentic risk

Overview

This read-only file summarizer has a confirmed path-handling flaw that can read outside the intended workspace despite claiming path validation.

Review before installing. The skill is not destructive and does not show network exfiltration, but it should not be trusted with sensitive workspaces until path resolution is constrained to the workspace root and triggers are narrowed to explicit file-summary requests.

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: 97% confidence
Finding: The trigger phrases "summarize" and "summary" are very generic and likely to match ordinary user requests unrelated to this specific skill, causing unintended invocation. Because the skill has workspace.read permission and reads files from the workspace, accidental trigger collisions could expose or process local file contents when the user did not explicitly intend to invoke this capability.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal