Security audit

Ads Optimizer Skill

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Amazon Ads reporting skill that uses expected credentials and Amazon network calls, with some safety notes around secret handling and output paths.

Install only if you are comfortable letting the agent use Amazon Ads credentials for reporting. Keep amazon-ads-api.json out of source control, restrict its filesystem permissions, use the least-privileged Ads access available, review any --out path before running, and treat this version as a reporting tool rather than a true bid or keyword optimizer.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill documentation indicates it requires environment-variable access and network connectivity to read credentials and call the Amazon Ads API, but it does not declare those permissions explicitly. This creates a transparency and governance gap: operators may approve or run the skill without understanding that it can access local secrets and make outbound requests to external endpoints.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access, suspicious.exposed_secret_literal

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/ads.js:12

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: scripts/ads.js:32