Icontact

Security checks across malware telemetry and agentic risk

Overview

This is a plausible iContact integration, but it gives an agent broad authenticated access to customer marketing data with weak scoping and safety guidance.

Install only if you trust Membrane and intend to connect an iContact account. Before allowing the agent to delete records, schedule or send emails, bulk-change contacts or lists, or use raw proxy requests, require it to show the exact target and get explicit confirmation. Verify the real iContact action schemas because the skill metadata and documentation links contain clear mismatches.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 82% confidence
Finding: The skill advertises destructive delete operations without any guidance to require user confirmation, preview affected records, or use safeguards before execution. In an agentic context, this increases the risk of accidental or unauthorized destructive actions against customer contact and campaign data.

Missing User Warnings

Low

Confidence: 68% confidence
Finding: The direct API proxy feature enables arbitrary requests to the external IContact service using an authenticated connection, but the documentation omits safety guidance about data transmission, endpoint scoping, and user awareness. In an LLM-driven toolchain, this can encourage overbroad external data access or exfiltration through raw requests beyond curated actions.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal