Issue Reproducer

Security checks across malware telemetry and agentic risk

Overview

This skill is a local bug-report formatting helper; its file input/output and optional Python script are disclosed and user-directed.

Install only if you want a local helper for formatting bug reports. When running the script, pass only the specific bug material you intend to process, avoid sensitive inputs when possible, and choose the output path deliberately because the script can write or overwrite a report file.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (4)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill declares no explicit permissions, yet its instructions include reading local resource files, writing output files, and optionally invoking a shell command via python3. This creates a transparency and policy-enforcement gap: a reviewer or runtime may assume the skill is low-risk while it can still access the filesystem and execute local code.

Description-Behavior Mismatch

High

Confidence: 96% confidence
Finding: The dispatcher enables several analysis modes such as directory auditing, CSV auditing, pattern scanning, and skill auditing that are outside the stated purpose of an issue reproduction skill. This kind of capability expansion increases the skill's access to local data and can be used to inspect repositories or files the user did not intend to expose, creating unnecessary data discovery and scope-creep risk.

Context-Inappropriate Capability

High

Confidence: 97% confidence
Finding: The built-in regex scanner searches files for secrets, private URLs, and dangerous shell patterns, which is unrelated to reproducing bugs from a description. In this skill context, that turns the tool into a lightweight code/content inspection utility that can surface sensitive material from local files, making misuse or accidental over-collection more likely.

Context-Inappropriate Capability

Medium

Confidence: 92% confidence
Finding: Directory reporting enumerates local files and extracts Markdown headings, while related audit features summarize repository contents rather than reproduce a bug. In a bug reproduction skill, this broader filesystem inspection is unjustified and can reveal internal project structure or document contents beyond the user's intended input.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal