ClawHub
Back to skill

Security audit

Cinematic Business Card Prospecting

Security checks for vulnerabilities and agentic risk

Overview

This skill is a sales outreach tool that appears purpose-aligned, but it handles business-card contact data and SMTP email sending without enough privacy, consent, retention, or anti-spam controls documented.

Review carefully before installing. Use this only for contacts you are allowed to process and email, store SMTP credentials securely, confirm every message before sending, and maintain opt-out/suppression records. Treat business-card photos and extracted lead data as personal data and decide where it may be sent, stored, and deleted.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README promotes automated extraction of business-card data, external brand research, and email outreach without disclosing privacy, consent, retention, or third-party data sharing implications. Because the workflow processes personal contact data and likely transmits it to external AI, research, and SMTP services, users may unknowingly handle regulated or sensitive personal information in ways that create privacy, compliance, and reputational risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly requires SMTP credentials and processes business card data, which commonly includes personal contact information. The documentation does not warn users about secure handling, storage, transmission, or consent/privacy obligations, increasing the chance that sensitive data and email credentials will be exposed, mishandled, or used in non-compliant outreach workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly advertises business card prospecting, researched leads, and email outreach without any mention of consent, opt-in, suppression handling, or jurisdiction-specific compliance. In the context of sales automation plus SMTP and vision capabilities, this creates a credible risk of enabling unsolicited contact, privacy misuse from business card data, and anti-spam or data-protection violations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This manifest description lists broad capabilities like 'Snap photos, get researched leads, send branded emails' but provides no specific invocation phrases, activation boundaries, or exclusions. In a manifest file, such open-ended wording can contribute to ambiguous triggering because it does not clarify when the skill should or should not be invoked.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.