Job Search MCP
Verdict safe, but 2 findings (2 medium), mainly data exfiltration. Most recent scan 2026-02-06.
The Job Search MCP skill is a relatively safe wrapper around the JobSpy MCP server with LOW to MEDIUM severity issues. The skill itself contains no malicious code, prompt injection attempts, or data exfiltration logic. The primary concerns are: (1) missing optional metadata fields that would improve transparency, (2) incomplete documentation, (3) supply chain risks from unpinned dependencies and unverified external repository clones. The skill functions as a documentation/configuration guide rather than executable code, which limits its attack surface. The main risks are indirect - users could install compromised versions of dependencies or clone a malicious repository if the external sources are compromised. No direct security threats (prompt injection, credential theft, command injection) were detected in the skill content itself.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Search for jobs across LinkedIn, Indeed, Glassdoor, ZipRecruiter, Google Jobs, Bayt, Naukri, and BDJobs using the JobSpy MCP server.
- Package
- 2 files, 18 KB
- SKILL.md
- 2105 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: Job Search MCP Skill · When to Use This Skill · Prerequisites · Installation & Setup · Option 1: Python MCP Server (Recommended) · Install with pip · Or install with uv (faster) · Option 2: Clone a Pre-built Server · Clone the jobspy-mcp-server repository · Install dependencies · or · Claude Desktop Configuration
Findings
MEDIUM External Dependency Installation Without Version Pinning Data Exfiltrationllm
The installation instructions recommend installing dependencies without pinned versions (e.g., 'mcp>=1.1.0', 'python-jobspy>=1.1.82'). This creates supply chain risk as future versions could introduce malicious code or breaking changes.
SKILL.md
pip install mcp>=1.1.0 python-jobspy>=1.1.82 pandas>=2.1.0 pydantic>=2.0.0MEDIUM Unverified External Repository Clone Data Exfiltrationllm
The skill instructs users to clone an external GitHub repository (github.com/chinpeerapat/jobspy-mcp-server) without providing verification mechanisms (commit hash, GPG signature, checksum). This creates supply chain risk as the repository could be compromised or modified after publication.
SKILL.md
git clone https://github.com/chinpeerapat/jobspy-mcp-server.gitWhat is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 15 KB |
example_calls.md | doc | 2.8 KB |
External hosts referenced
indeed.com github.com linkedin.com techcorp.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/job-search-mcp
- Raw scan result: job-search-scan.json
- Badge for your README:
- Request a re-scan