Doc Summarize Pro

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:18 PM UTC
• Version:
  3.0.0

Overview

This is a local document summarizer with accuracy and local-history privacy caveats, but no evidence of hidden access, exfiltration, or destructive behavior.

Install only if you are comfortable with a local history file at $HOME/.doc-summarize-pro/history.log recording processed file paths and commands. Do not rely on translate-summary for actual translation, and verify summaries before using them for important decisions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Description-Behavior Mismatch

Medium

• Confidence: 96% confidence
• Finding: The skill advertises a translate-and-summarize capability, but the implementation only echoes the original text and extracts a few sentences without performing any translation. This is a deceptive capability mismatch that can mislead users or downstream agents into trusting output as translated content, causing incorrect decisions, workflow failures, or disclosure of untranslated sensitive material to the wrong audience.

Description-Behavior Mismatch

Low

• Confidence: 88% confidence
• Finding: The skill is marketed as an enhanced or smart summarizer, but the code performs only basic truncation, sentence splitting, and simple keyword matching. While this is not code-execution dangerous, it is a trust and integrity issue: users may rely on the tool for higher-quality analysis than it can provide, which can degrade decision-making in security, legal, or business contexts.

Intent-Code Divergence

Medium

• Confidence: 95% confidence
• Finding: The translate-summary command name and banner imply translation is performed, but the inline note explicitly says full translation requires another tool. This contradiction increases the risk of user confusion and unsafe reliance on mislabeled output, especially in automated pipelines that may treat the result as translated text.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill states that it stores processing history with timestamps under $HOME/.doc-summarize-pro/history.log, but it does not warn users that filenames, paths, and potentially sensitive document usage patterns may be retained on disk. On shared systems or compromised accounts, this metadata could reveal confidential project names, document locations, or user activity over time.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The script persistently records every processed command and file path to ~/.doc-summarize-pro/history.log without any explicit user notice, consent, or opt-out. In a document-processing skill, file paths can reveal sensitive project names, usernames, client names, or confidential directory structures, so this creates a privacy and metadata leakage risk even though it is not overtly malicious.

VirusTotal

65/65 vendors flagged this skill as clean.