Security audit

B2B Lead Generation Scraper

Security checks for vulnerabilities and agentic risk

Overview

This skill needs review because it asks for a LinkedIn session cookie and bulk-collects personal lead data while retaining raw data and explicitly throttling to avoid detection.

Install only if you have clear authorization to collect this data and use the target sources this way. Treat LI_SESSION as a live account credential, prefer official APIs or approved data providers, revoke the session after use, and define strict limits for raw data storage, CSV sharing, retention, and deletion before running it.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:25
Finding: Authenticated Session Cookie Handling Creates Credential Exposure Risk
Content: View full analysis
Remediation: View remediation

other

Error

Location: SKILL.md:12
Finding: Bulk Personal-Data Collection With Unbounded Raw-Data Retention
Content: View full analysis
Remediation: View remediation

other

Warning

Location: SKILL.md:48
Finding: Scraping Rule Explicitly Encourages Avoidance of Platform Detection
Content: View full analysis
Remediation: View remediation

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 (2)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill instructs users to extract and store a live LinkedIn session cookie (li_at) without clear warnings about credential sensitivity, account takeover risk, or platform-policy implications. A browser session cookie is effectively an authentication token, so mishandling it can expose the user's account and enable unauthorized scraping or impersonation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The usage section provides example prompts like "Generate a lead list" and "Export leads to CSV" without defining exact trigger phrases, constraints, or exclusion conditions. In a markdown skill description, this can make activation scope ambiguous because these requests resemble common business requests rather than narrowly scoped invocations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.