Ads Data Query

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only ads reporting helper that may give broad campaign recommendations but does not contain code, credentials, or account access.

Install as an advisory planning/reporting skill. Review any budget, bidding, campaign, or handoff recommendations before applying them in an ad account, and avoid sharing more confidential performance data than needed.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger keywords are broad enough to match many generic business or marketing requests, which can cause the skill to activate outside its intended scope. In an agent environment, unintended invocation can route user requests into ad-optimization workflows that produce irrelevant or overly action-oriented outputs, increasing the chance of unsafe automation or incorrect downstream handoffs.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The activation rules combine distinct functions—analysis, campaign execution, and general optimization—without clear separation, making it ambiguous when this skill should run. That ambiguity is risky because a skill described as a query assistant may be invoked for operational campaign actions, causing scope creep, inappropriate recommendations, or accidental chaining into execution-capable systems.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal