Security audit

Knowledge Cards Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward document-to-study-card helper with a small PDF text extraction script and no hidden network, credential, persistence, or destructive behavior.

Install this if you want local document-to-card conversion. Use caution with PDFs from untrusted sources, keep pypdf updated, and confirm any local file path before allowing the agent to read it.

SkillSpector

By NVIDIA

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: This is a mismatch because the declared purpose says the skill converts multiple kinds of inputs into knowledge cards, but the provided code does not generate cards at all and does not handle articles, Markdown, or TXT files. Its actual function is a narrow utility: PDF text extraction only. There is no hidden behavior or resource access beyond the declared domain, but the primary purpose differs materially from the description.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The skill instructs the agent to produce output in Chinese or English based solely on the source text's language, and to use the dominant language for mixed-language input. This imposes a language-selection policy without explicitly offering the user a choice or opt-in, which matches the language/locale policy violation criteria.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: This manifest file defines activation triggers, so vague-trigger review applies. The single-word trigger "flashcards" is broad and could overlap with general conversation or unrelated study requests, and the manifest provides no narrowing context or exclusion examples to reduce unintended invocation.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: "study cards" is a generic phrase that may appear in ordinary educational discussion rather than a clear invocation. The manifest does not define boundaries, negative examples, or contextual constraints, so activation conditions remain underspecified.

Unpinned Dependencies

Low

Category: Supply Chain
Content: pypdf>=4.0.0
Confidence: 50% confidence
Finding: pypdf>=4.0.0

Known Vulnerable Dependency: pypdf==4.0.0 — 10 advisory(ies): CVE-2026-48156 (pypdf: Possible long runtimes for zero-only width values in cross-reference stre); CVE-2026-24688 (pypdf has possible Infinite Loop when processing outlines/bookmarks); CVE-2026-27628 (pypdf has a possible infinite loop when loading circular /Prev entries in cross-) +7 more

Low

Category: Supply Chain
Confidence: 60% confidence
Finding: pypdf==4.0.0

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.