Security audit

Lead Hunter

Security checks across malware telemetry and agentic risk

Overview

This lead-generation skill is coherent with its purpose, but it handles personal lead data, scraping, email probing, webhooks, and outreach triggers with enough under-scoped compliance and user-control concerns to require review before installation.

Install only if you have a lawful, consent-aware lead-generation workflow. Before use, disable or gate automated outreach, avoid scraping where terms do not allow it, minimize collected fields, do not send full lead records to untrusted webhooks, and store generated lead files securely with retention and deletion rules.

SkillSpector

By NVIDIA

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 (9)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly markets automated lead generation and enrichment using emails, socials, phone lookup, and company data, but provides no privacy, consent, or lawful-use guardrails. In this context, omission is dangerous because it normalizes collection and resale of personal contact data without notice about applicable data protection, anti-spam, and platform-policy constraints.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill advertises 'Auto-outreach' and 'Outreach sequence triggers' as outputs without warning that the agent may send messages or trigger external actions automatically. In a lead-generation skill, this increases the risk of spam, unauthorized contact, policy violations, and reputational or legal harm if the automation acts without human approval, recipient consent, or rate/approval controls.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The GitHub discovery section explicitly collects and outputs personal contact data such as public email, location, company, and linked social handles for lead generation without any privacy notice, lawful-basis guidance, or handling constraints. In the context of an automated prospecting skill, this increases the risk of privacy violations, unsolicited outreach, and noncompliant processing of personal data at scale.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The Product Hunt section states that discovery is performed via scraping because there is no official API, but it does not warn users about legal, terms-of-service, or blocking risks. That omission is dangerous because it normalizes potentially unauthorized collection behavior and can expose users to account bans, IP blocking, or policy violations when automated at scale.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The Moltbook section outputs owner_email alongside owner_handle and owner_twitter, directly linking identities and contact details without any warning about sensitive personal data handling. In a lead-enrichment tool, this makes misuse easier by enabling identity correlation and direct outreach, amplifying privacy and abuse risk beyond simple public-profile discovery.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The orchestration section writes aggregated lead data from multiple sources into combined output files on disk without warning that personal data will be stored persistently. Aggregation raises sensitivity because merged records can create richer profiles than any single source, increasing exposure in the event of unauthorized access, accidental sharing, or over-retention.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: This section operationalizes collecting and verifying personal email addresses via scraping, public-source mining, pattern guessing, SMTP probing, and third-party enrichment APIs without any guidance on consent, lawful basis, terms-of-service compliance, or data-sharing restrictions. In a lead-generation skill, that omission can directly enable privacy-invasive collection and external disclosure of personal data, increasing legal, compliance, and reputational risk.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The webhook configuration sends the full lead object to an arbitrary external URL, but the documentation does not warn that personal and enrichment data may be transmitted outside the primary system boundary. In a lead-generation skill, that can include emails, phone numbers, social profiles, and company intelligence, increasing the risk of unintended data disclosure, privacy violations, and unsafe downstream automation.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill describes automated lead enrichment, scoring, and outreach-triggering behavior without warning users that these actions may involve collecting personal/professional data and initiating contact based on that data. In a lead-generation context, omission of privacy and consent considerations can cause users or downstream agents to perform non-compliant enrichment and outreach workflows without appropriate safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.