AI Job Hunter Pro

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.3.0

Overview

This skill mostly matches its job-search purpose, but needs review because it handles sensitive resume data and can generate application materials with hard-coded personal claims.

Install only after reviewing the scripts and keeping dry-run plus explicit confirmation enabled. Manually verify every generated cover letter, remove the hard-coded Disney/Amazon/UCL claims unless they are truly yours, use a virtual environment, and treat the local Chroma/SQLite databases and any logged-in job-site browser sessions as sensitive.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (11)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 96% confidence
• Finding: The skill invokes Python scripts that read local files, write local state, access external job platforms, and execute shell commands during setup, but it does not declare any permissions for those capabilities. This creates a trust and containment gap: a user or platform may approve the skill without understanding it can access sensitive resume/profile data, modify local files, and communicate over the network.

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: The dashboard imports executable JavaScript from cdnjs and fonts from Google Fonts, which creates unnecessary outbound network access and a supply-chain dependency for a tool whose stated purpose is local visualization of a user-provided JSON file. If either third-party resource is compromised, blocked, or replaced, the page could run attacker-controlled code or leak usage metadata despite handling potentially sensitive job-search data.

Context-Inappropriate Capability

Medium

• Confidence: 80% confidence
• Finding: The skill accepts user-provided resume files and passes them to external document-processing binaries, which adds unnecessary OS-level parsing capability to a job-matching workflow. While not an immediate injection flaw, this meaningfully enlarges the attack surface because malformed documents may trigger vulnerabilities in pdftotext or pandoc.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README explicitly promotes automated application submission and "auto-apply" behavior but does not clearly warn users that the skill may take actions on external job-platform accounts, submit data on their behalf, or cause irreversible profile/application changes. In a job-search automation context, this omission is meaningful because users may underestimate the risk of mass submissions, accidental applications, account flags, or privacy exposure when resumes and cover letters are sent to third parties.

Missing User Warnings

Medium

• Confidence: 79% confidence
• Finding: The pipeline automatically loads sensitive profile data from a predictable local file and then persists derived personal content, including cover letters and ATS keywords, into a local SQLite database without explicit notice or consent flow. In a job-search skill, this increases privacy risk because resumes and application materials often contain PII, employment history, and other sensitive career data that may be retained longer than the user expects.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: Resume chunks and embeddings are persisted to a local Chroma database under the user's home directory without any explicit consent, retention policy, or deletion workflow. Because resumes commonly contain highly sensitive personal data, silent long-term storage increases privacy and data-exposure risk, especially on shared or compromised systems.

Missing User Warnings

Low

• Confidence: 82% confidence
• Finding: The feedback mechanism stores user-derived job-description data and preference signals persistently without clear notice or retention controls. Even if lower sensitivity than a resume, this still creates an unannounced behavioral profile and may reveal the user's interests or job-search activity over time.

Unpinned Dependencies

Low

• Category: Supply Chain

Content

chromadb>=0.4.0
sentence-transformers>=2.2.0
pdfplumber>=0.10.0
python-docx>=0.8.11

• Confidence: 95% confidence
• Finding: chromadb>=0.4.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

chromadb>=0.4.0
sentence-transformers>=2.2.0
pdfplumber>=0.10.0
python-docx>=0.8.11

• Confidence: 95% confidence
• Finding: sentence-transformers>=2.2.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

chromadb>=0.4.0
sentence-transformers>=2.2.0
pdfplumber>=0.10.0
python-docx>=0.8.11

• Confidence: 95% confidence
• Finding: pdfplumber>=0.10.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

chromadb>=0.4.0
sentence-transformers>=2.2.0
pdfplumber>=0.10.0
python-docx>=0.8.11

• Confidence: 98% confidence
• Finding: python-docx>=0.8.11

VirusTotal

65/65 vendors flagged this skill as clean.