Security audit

Kol Outreach

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only outreach template skill with no hidden execution, data access, persistence, or credential handling.

Use this as a template library, not an automated sending system. Before applying the outreach advice, users should follow anti-spam laws, platform rules, recipient-consent expectations, and avoid deceptive or mass unsolicited outreach.

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: 90% confidence
Finding: This markdown file describes DM and cold-email outreach workflows, including follow-up cadence and deliverability setup, but does not include any warning that these actions may implicate anti-spam rules, platform terms, or recipient consent expectations. For markdown files, SQP-2 applies when descriptions omit warnings about behaviors that could affect privacy or system integrity; unsolicited outreach to individuals can affect recipient privacy and account safety.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The file content is fully Korean-language instructional text and does not indicate that the user can choose another language or that the skill is intentionally limited to Korean-speaking users. Under SQP-3, forcing a specific language without user opt-in is a natural-language policy concern unless clearly justified as region-specific.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.