ClawHub
Back to skill

Security audit

Leadgenius

Security checks for vulnerabilities and agentic risk

Overview

This lead-enrichment skill is mostly coherent, but it asks for broad third-party and CRM authority that can transmit and modify business contact data at scale without tight confirmation boundaries.

Review before installing if your lead data, CRM, or Slack workspace contains sensitive business or personal data. Only use approved API credentials, confirm the exact dataset and destination before enrichment or sync, and avoid enabling automatic updates or merges until field mappings, consent obligations, retention, and rollback procedures are clear.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
"files": ["SKILL.md"],

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description is overly broad and could cause the agent to invoke this capability for generic sales, marketing, or contact-management requests without clearly establishing when external enrichment, scoring, or CRM actions are appropriate. In context, that increases the chance of unintended processing or transmission of business contact data to third-party services without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The examples encourage uploading prospect datasets and syncing them to Salesforce/Slack without an upfront warning that contact and company data will be transmitted to external systems. Given the skill's purpose, this omission could normalize sensitive-data transfer before users are prompted to verify authorization, data sensitivity, or compliance requirements.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 138)May include surrounding context.

bash
# LeadGenius API credentials
export LEADGENIUS_API_KEY="sk_live_1234567890abcdef"
export LEADGENIUS_BASE_URL="https://api.leadgenius.io/v2"

# CRM Integration (choose one or configure multiple)
export SALESFORCE_ORG_ID="00D123456789ABCDE"

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 322)May include surrounding context.

md
### What LeadGenius Will NOT Do
- **Will NOT provide personal data on non-business contacts** (home addresses, family information, social security numbers)
- **Will NOT bypass GDPR, CCPA, or data privacy regulations** even if requested
- **Will NOT enrich contacts without consent confirmation** when required by applicable law
- **Will NOT access or modify your CRM without explicit API credentials and permission**
- **Will NOT guarantee 100% accuracy** for all enrichment fields; some lookups have confidence scores below 100%
- **Will NOT process data outside the EU if EU data residency is required**

Static analysis

No suspicious patterns detected.