ClawHub
Back to skill

Security audit

SkillForge — Self-Evolving AI Skills

Security checks across malware telemetry and agentic risk

Overview

SkillForge is transparent and local, but it asks the agent to monitor private work history and conversations broadly enough that users should review its scope before installing.

Install only if you are comfortable with local logs, memory files, conversation history, and existing skills being analyzed for workflow patterns. Narrow or avoid broad triggers, disable weekly auto-scan and real-time detection unless you explicitly want ongoing monitoring, add exclusions for sensitive logs, and manually review every generated or merged skill draft before approving it.

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
88% confidence
Finding
The trigger list includes very broad and common terms such as "pattern," "evolve," and "review"-like phrases that can plausibly appear in ordinary conversation. In a meta-skill that scans logs, generates reports, and creates draft files/directories, unintended activation can cause unplanned analysis of user history and filesystem writes, even if it does not auto-install skills.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.