ClawHub
Back to skill

Security audit

Ad Test Designer

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ad experiment planning and read-out helper with user-controlled memory saving and no hidden destructive behavior.

Install only if you are comfortable giving the agent your own exported ad-test metrics or summaries. Review any proposed business action yourself; the skill is designed to keep decisions tied to a precommitted owner and rule, and memory saving should happen only after you approve it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Save Results

After delivering, ask "Save this test design / read-out for future sessions?" If yes, write a dated summary to `memory/ad/ad-test-designer/YYYY-MM-DD-<topic>.md` with the hypothesis, design parameters, effect/uncertainty read, guardrails, decision owner/rule, and any approved action. Do not write memory without asking.

## Reference Materials
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.