hr-recruitment-jd-generator

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 9:52 AM UTC
• Version: 1.0.0

Overview

This skill is a coherent HR job-description generator with disclosed local file output and optional user-configured LLM enhancement; no hidden exfiltration, destructive behavior, or deceptive instructions were found.

Install only in a workspace where creating HR recruitment files is intended. Leave LLM_* unset for fully local rule-based generation, or configure them only with an approved endpoint because job descriptions and hiring details will be sent there. Pin or separate the pytest dependency before using this in controlled CI or production packaging.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• 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

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill instructs use of environment variables, file creation, file reads, and a CLI invocation that may rely on networked model endpoints, yet it declares no permissions or capability boundaries. This creates a governance gap: an agent may perform sensitive operations without explicit user-visible authorization, increasing the risk of unintended file access, workspace modification, or outbound data transfer.

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The trigger text is broad enough to match common HR or drafting requests, which can cause the skill to activate in situations the user did not intend. Over-broad activation increases the chance of unnecessary file initialization, CLI execution, or collection of structured job data when a simple conversational response would have been safer and more appropriate.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The code serializes the entire job object and sends it to a configurable external endpoint without any visible consent, disclosure, or minimization controls in this file. If job data includes internal hiring plans, compensation details, candidate-related notes, or other sensitive HR information, this can create an unintended third-party data exposure risk.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

pytest

• Confidence: 97% confidence
• Finding: The dependency is unpinned, so installs may resolve to different pytest versions over time, reducing build reproducibility and potentially pulling in a newly vulnerable or incompatible release. In this case the risk is amplified because the same dependency is also flagged with a known vulnerability, and leaving it unpinned makes controlled remediation harder.

Known Vulnerable Dependency: pytest — 2 advisory(ies): CVE-2025-71176 (pytest has vulnerable tmpdir handling); CVE-2025-71176 (pytest has vulnerable tmpdir handling)

High

• Category: Supply Chain
• Confidence: 88% confidence
• Finding: If the installed pytest version is affected by the cited tmpdir-handling vulnerability, an attacker may be able to abuse test-time filesystem behavior to access or manipulate unintended paths during CI or local execution. Even though pytest is typically a development dependency, it often runs in privileged CI environments and can expose secrets, alter artifacts, or compromise pipeline integrity.

Static analysis

No suspicious patterns detected.