Implementation Readiness Checker

• Outcome: Pass
• Latest audit: May 29, 2026, 8:22 PM
• Version:
  1.0.0

Overview

The skill appears to be a local readiness/audit helper that scans files and writes reports, with no evidence of exfiltration, destructive behavior, or persistence.

Install only if you want a local checker to inspect the project or skill files you point it at. Run it from a narrow workspace, review where it writes output, and avoid invoking it on home directories, credential stores, or unrelated private projects.

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: 88% confidence
• Finding: The skill advertises and instructs use of local file reads, file writes, and shell execution via `python3 .../scripts/run.py`, but does not declare corresponding permissions or constraints. This creates a capability transparency problem: callers and policy systems may treat the skill as low-risk while it can actually access local data and execute code, increasing the chance of unintended data exposure or unsafe execution.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 93% confidence
• Finding: The declared purpose is a readiness checker, but the analyzed behavior indicates substantially broader functionality: directory scanning, regex-based content inspection, skill integrity auditing, data profiling, and writing rendered output. This mismatch is dangerous because it can conceal security-relevant behavior behind an innocuous description, causing users or automated governance to authorize a skill that can inspect sensitive files and produce artifacts outside the expected scope.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger examples are broad natural-language phrases that can overlap with ordinary project discussion, increasing the chance that the skill is invoked unintentionally. In a gating/readiness workflow, accidental invocation can misroute user intent, generate misleading readiness assessments, or interfere with approval-related processes even if the skill itself is read-only.

VirusTotal

66/66 vendors flagged this skill as clean.