Security audit

Indeed Full

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed RolesAPI wrapper for Indeed job data, with no hidden persistence, destructive behavior, or unrelated data access in the artifacts.

Install only if you are comfortable sending job searches, locations, job keys, and pasted Indeed URLs to RolesAPI using your ROLESAPI_KEY. Treat account and usage checks as exposing your RolesAPI plan, rate limit, credit balance, and recent usage to the agent output.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill explicitly requires an API key and calls external RolesAPI endpoints, but the manifest does not declare permissions for environment access and network use. This creates a transparency and governance gap: users or platforms may not realize the skill can read secrets and transmit user-supplied job queries and URLs to a third party.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 84% confidence
Finding: The skill description focuses on job-posting retrieval, but the documented behavior also includes account inspection (/v1/me, /v1/usage) and URL-based role fetching. That mismatch can mislead users and reviewers about the full data-access surface, including exposure of account metadata, usage history, and transmission of pasted Indeed URLs to a third-party service.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.