Skill Market Fit Ranker

• Outcome: Pass
• Latest audit: May 29, 2026, 8:25 PM
• Version:
  1.0.0

Overview

This skill is a local market-fit ranking helper with a disclosed Python script, and the reviewed artifacts do not show hidden network access, credential use, destructive actions, or persistence.

Install only if you are comfortable running a local Python helper from this publisher. Use it on intended input files, avoid feeding sensitive private material unless necessary, prefer dry-run/stdout first, and review the generated ranking before using it for publishing or roadmap decisions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill declares no permissions, yet its instructions explicitly permit running `python3` and reading local resources while also writing output files. This creates a capability/permission mismatch that can mislead users and any policy layer about what the skill may access or modify, increasing the chance of unintended local file access or shell execution.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The stated purpose is simple prioritization/ranking, but the detected behavior includes directory scanning, regex-based inspection for secrets or private URLs, structure auditing, spec-driven mode switching, and writing audit reports. That broader behavior materially expands the attack surface and could be used to inspect unrelated local content or produce outputs beyond the user’s expected scope, which is especially risky in a user-invocable skill.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger phrases shown in the README are short, generic everyday requests like '帮我给这批 skill 排序' and '综合高频和传播性', which are broad enough to match normal conversation outside a deliberate invocation context. This can cause unintended routing to the skill, leading to incorrect task selection, misleading outputs, or accidental processing of user content under the wrong workflow.

VirusTotal

64/64 vendors flagged this skill as clean.