ClawHub
Back to skill

Security audit

sdlc- get software development life cycle

Security checks across malware telemetry and agentic risk

Overview

The available evidence shows a broadly scoped planning skill concern, but no concrete sign of hidden, destructive, or credential-stealing behavior.

Install only if you want general SDLC planning help. Be aware it may activate for broad software-development questions, so prefer more specific skills for coding, debugging, architecture, security review, or document-generation tasks when those are what you actually need.

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
91% confidence
Finding
The skill description is extremely broad and is likely to trigger on a wide range of ordinary software-development questions, causing the skill to activate when a more specific or safer skill should handle the request. Over-broad activation expands the skill's effective attack surface, increases unintended invocation, and can lead to incorrect routing, unnecessary file reads, or cross-skill chaining such as suggesting use of the `docx` skill when not needed.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.