php-pro

Security checks across malware telemetry and agentic risk

Overview

This is a PHP development guidance skill with no executable code or hidden install behavior.

Use this skill for PHP repositories you are comfortable letting an agent read and edit. Review generated changes before committing or deploying, and avoid sharing production secrets unless a specific trusted task clearly requires them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill defines behavior under a generic 'When invoked' heading without clear trigger conditions, boundaries, or scope constraints. In an agent environment, this can cause over-broad activation or use in unintended contexts, increasing the chance the skill will inspect project files or influence actions when the user did not explicitly request PHP-specific analysis or implementation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal