"dataify-linkedin-company-information-by-url"

• Outcome: Review
• Latest audit: Sep 1, 2026 · 9:32 AM UTC
• Version: 1.3.0

Overview

The skill is advertised as LinkedIn company-URL collection, but its instructions also expose LinkedIn job scraping through an authenticated Dataify workflow.

Install only if you intend to use Dataify for this broader LinkedIn scraper family, not just company URLs. Review the job-scraping options and token setup carefully, and prefer session-scoped API-token configuration unless you deliberately want a permanent shell variable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The skill metadata says it is limited to LinkedIn company URLs, but the workflow instructs users to choose from unrelated job-listing and keyword tools. This scope expansion can cause the agent to operate on unintended targets and data types, increasing the risk of collecting the wrong data and violating least-privilege/task-boundary expectations.

Intent-Code Divergence

Medium

• Confidence: 92% confidence
• Finding: The quick start frames the skill as a single-purpose LinkedIn company info collector, but later instructions broaden behavior to multiple other tools. This inconsistency is dangerous because operators and higher-level agents may trust the narrow description while the skill actually enables broader data collection actions.

Description-Behavior Mismatch

High

• Confidence: 95% confidence
• Finding: The skill metadata says it is for LinkedIn company information by URL, but the workflow explicitly offers unrelated job-listing URL, job URL, and keyword scraping tools. This scope expansion can cause the agent to invoke capabilities the user did not intend, increasing the risk of unauthorized or policy-noncompliant data collection.

Intent-Code Divergence

Medium

• Confidence: 94% confidence
• Finding: The documentation presents the skill as rooted in linkedin_company_information_by-url, yet the operational steps broaden it to unrelated job-scraping tools. This mismatch weakens user consent and reviewability because the declared purpose does not match the actual reachable actions.

Description-Behavior Mismatch

High

• Confidence: 96% confidence
• Finding: The skill is described as collecting LinkedIn company information by URL, but the tool parameter file exposes additional job-listing and keyword-based job collection capabilities. This scope mismatch can let an agent invoke unintended data-access paths, bypass user expectations, and expand collection into recruitment or profiling workflows not disclosed by the manifest.

External Transmission

Medium

• Category: Data Exfiltration

Content

13. Set `spider_name` to `linkedin.com`.
14. Set `spider_id` to the selected tool's `tool_sign`.
15. Always include `spider_errors=true` and `file_name={{TasksID}}`.
16. Return a curl command for `https://scraperapi.dataify.com/builder`.

## Set DATAIFY_API_TOKEN

• Confidence: 89% confidence
• Finding: The skill explicitly instructs construction of authenticated requests to an external service and transmission of scraped parameters/results context to `scraperapi.dataify.com`. External transmission is expected for this skill's purpose, but it is still security-relevant because it sends user-supplied targets and uses bearer-token-authenticated API access to a third party.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.