career-site-job-listings-scraper-api-skill

• Outcome: Review
• Latest audit: Sep 8, 2026 · 4:36 PM UTC
• Version: 1.0.0

Overview

The skill appears to run the advertised BrowserAct career-page scraper, but it needs review because it asks users to provide an API key directly to the agent and may activate for overly broad scraping requests.

Review before installing. Use it only for public career pages approved for BrowserAct processing, and configure BROWSERACT_API_KEY through a secure environment or secret-management mechanism rather than pasting the key into chat. Be aware that the supplied URL and extracted results are processed by BrowserAct.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 80% confidence
• Finding: The skill declares runtime requirements for an environment variable and invokes a Python script that calls an external API, but it does not clearly declare or surface equivalent permissions to users. This creates a transparency gap: users may not realize the skill can access secrets from the environment and transmit user inputs or extracted data over the network to BrowserAct.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The description contains broad trigger phrases such as exporting public records, enriching datasets, and monitoring public web data, which can cause the skill to activate for generic scraping or data-processing requests outside its narrow purpose. Overbroad activation increases the chance of unintended execution, sending unrelated user-provided URLs or data to an external service without the user specifically intending to use this BrowserAct template.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The documentation explains how to run the scraper but does not clearly warn that user-supplied URLs, API credentials, and extracted results are sent to the external BrowserAct service. This omission can lead to uninformed disclosure of sensitive business targets, internal URLs mistakenly provided by users, or regulated data scraped from pages and transferred to a third party.

Ssd 3

Medium

• Confidence: 98% confidence
• Finding: The script explicitly tells the operator to 'Provide it to me' when the BrowserAct API key is missing, which creates a social-engineering path for credential disclosure to the agent instead of restricting secret handling to environment variables or a secure secret store. In an agent-skill context, this is dangerous because users may paste long-lived API credentials into chat or tool inputs that are logged, retained, or exposed beyond the intended execution boundary.

Static analysis

No suspicious patterns detected.