Security audit

Cold Email Copy

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple cold-email writing prompt, but it embeds off-platform payment requests and advertises unreviewed extra scripts.

Install only if you are comfortable with a skill that includes embedded commercial upsell content. The reviewed artifact does not execute code, but any paid assets or Python scripts offered through the payment links are outside this review and should be treated as untrusted until separately inspected.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Vague Triggers

Medium

Confidence: 85% confidence
Finding: This markdown file describes activation through generic example prompts like "Create a follow-up sequence" and "Generate 5 cold email subject lines" without clearly defining trigger boundaries or exclusion conditions. The lack of explicit trigger scope or negative examples increases the risk that normal writing-assistance requests could unintentionally invoke this skill.

Description-Behavior Mismatch

Medium

Confidence: 96% confidence
Finding: The skill metadata says it generates cold email copy, but the embedded content additionally solicits payment and advertises access to extra assets such as production-ready templates and Python scripts. This is a scope mismatch that can mislead users and downstream agents about the skill’s actual purpose, creating trust and supply-chain risk through undisclosed commercial or secondary functionality.

Context-Inappropriate Capability

Medium

Confidence: 98% confidence
Finding: Including PayPal payment solicitation and a cryptocurrency wallet address in a skill whose purpose is only copy generation is unjustified and introduces social-engineering and financial-abuse risk. An agent or user could be steered into off-platform payments or trust the skill as an endorsed commercial offer, especially because the solicitation is embedded alongside normal usage guidance.

Static analysis

No suspicious patterns detected.