Research Review Assistant

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.0

Overview

The skill’s research-review behavior mostly matches its purpose, but its dependency metadata creates a supply-chain concern that should be reviewed before installation.

Install only after correcting or removing the package.json dependency entries and auditing the actual runtime dependencies. Use explicit research-review commands to avoid accidental activation, and only enable the documented cron job if you want scheduled literature-review runs.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (2)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The manual trigger phrases are generic natural-language requests such as '帮我做…文献综述' and '迭代我的论文背景部分', which are likely to overlap with ordinary user conversations. In an auto-loaded skill system, this can cause unintended invocation, letting the skill activate on broad academic-assistance prompts without clear user consent or disambiguation.

Known Vulnerable Dependency: beautifulsoup4==4.12.0 — 1 advisory(ies): MAL-2025-3615 (Malicious code in beautifulsoup4 (npm))

High

• Category: Supply Chain
• Confidence: 94% confidence
• Finding: beautifulsoup4==4.12.0

VirusTotal

67/67 vendors flagged this skill as clean.