Security audit

Kol Creator Discovery

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AIsa API integration for creator discovery and contact-list reporting, with no evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Install only if you intend to use AIsa for influencer/contact research. Provide an AISA_API_KEY through your normal secret mechanism, review output paths because reports may contain personal contact data, and use the results only where you have an appropriate business purpose and authorization.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill declares required binaries and environment variables and explicitly instructs writing report files and making outbound API calls, but it does not declare an explicit permissions model for those capabilities. This creates a transparency and least-privilege issue: a harness or reviewer cannot easily distinguish expected network/file/env access from overbroad behavior, increasing the chance of unintended data exposure or unsafe execution in permissive runtimes.

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The README's invocation guidance is broad enough that the skill may be selected for loosely related tasks such as general YouTube search, trend discovery, channel research, or SERP analysis, even though it performs creator email lookup and outreach-list building. Over-broad routing increases the chance of unnecessary collection or use of personal contact data in contexts where the user did not explicitly request outreach or contact enrichment.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The README advertises verified email lookup, contact enrichment, and outreach-ready table generation without any visible privacy, consent, or acceptable-use warning. In a skill specifically designed for prospecting and influencer outreach, this omission makes it easier to normalize bulk collection and downstream use of personal contact information without appropriate user notice or policy checks.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The reference describes bearer-authenticated access and collection of creator emails and contact links, but provides no guidance on protecting API keys, minimizing retention of personal data, or obtaining/using contact data in a compliant way. In a skill explicitly built for outreach-list creation and email discovery, that omission increases the chance of insecure credential handling or privacy misuse by downstream implementers.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill performs bulk email enrichment and writes outreach-ready reports containing personal contact data, but it provides no consent, purpose-limitation, retention, or compliance guardrails. In this context, the skill is explicitly designed for prospecting and contact discovery, which increases the likelihood of privacy misuse, unauthorized processing, or downstream spam/abuse at scale.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.