Security audit

Katelynn Lead Gen

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent lead-generation skill, but it handles personal contact data, outbound routing, and cross-run memory without enough consent, privacy, or user-control boundaries.

Review before installing. Use only for lawful, permission-aware prospecting, keep exports limited to necessary business data, confirm before any SMS, phone transfer, or outreach action, and avoid letting the skill persist sensitive prospect details in learned-rules.md.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill advertises very broad trigger phrases and catch-all activation criteria, which can cause it to run in situations where a user did not clearly request prospecting, contact discovery, or outreach. Because this skill handles sensitive business contact research and can lead to outreach actions, overbroad activation increases the risk of unintended collection, profiling, or downstream contact actions without sufficiently explicit user intent.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill instructs the agent to collect, process, and act on personal/business contact data, including phone numbers, email addresses, SMS alerts, and warm call transfer details, but provides no user-facing privacy notice, consent boundary, retention policy, or safety guardrails. In this context, the agent is effectively enabling lead profiling and real-time routing of contact information, which can expose personal data, facilitate unsolicited outreach, and create compliance risk under privacy, telemarketing, and data-handling regimes.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The README explicitly states the skill returns and exports personal contact information such as names, titles, company details, LinkedIn URLs, and email addresses, but provides no warning about privacy, consent, lawful basis, retention, or acceptable-use constraints. In a lead-generation and outreach skill, this omission can normalize bulk collection and processing of personal data in ways that may violate privacy laws, platform terms, or internal compliance requirements.
Content: No source excerpt is available for this finding.

Ssd 3

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill directs the system to write new learned rules from prior runs to a persistent markdown file and reuse them in future runs, creating a natural-language memory channel outside structured controls. This can retain sensitive prospecting outcomes, customer exclusions, or operational judgments across sessions without visibility, retention limits, sanitization, or user approval, increasing the risk of data leakage and unintended cross-run influence.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill explicitly advertises prospect discovery, company research, and personalized cold outreach, and its metadata declares external tooling such as WebSearch and WebFetch. Without any warning, consent boundary, or privacy-use guidance, users may cause the agent to collect, process, and act on personal or company data in ways that create privacy, compliance, and anti-spam risk. In this context, the danger is elevated because the skill is purpose-built to scale research and outreach rather than incidental web use.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.