MockAPI - Instant REST API from JSON
Verdict safe, but 3 findings (2 medium, 1 low), mainly social engineering, data exfiltration, unauthorized tool use. Most recent scan 2026-02-06.
This skill has MEDIUM severity security concerns. The primary issue is that it's not actually a functional agent skill - it's merely documentation for an external npm package disguised as a skill. This is deceptive packaging (social engineering). The skill contains no agent instructions, no executable code, and provides no actual agent functionality. Additionally, it references a missing 'a.py' file with no explanation, and instructs users to globally install an unpinned third-party npm package without security warnings. The skill lacks proper metadata (license, compatibility, allowed-tools). While there's no active malicious code present, the deceptive nature and potential for tool exploitation via external package installation warrant caution. This appears to be either a misunderstanding of what agent skills are, or an attempt to use the skills system for package promotion/distribution.
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
Spin up a mock REST API server from JSON files in seconds. Full CRUD, filtering, pagination. Zero config. Free CLI tool for frontend developers.
- Package
- 1 file, 2.1 KB
- SKILL.md
- 278 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: MockAPI · Installation · Quick Start · Create example db.json · Start server · Data File Format · Generated Routes · Query Parameters · Filter · Pagination · Sort · Options
Findings
MEDIUM Misleading Skill Description - Not an Agent Skill Social Engineeringllm
The skill presents itself as 'MockAPI - Instant REST API from JSON' but is actually documentation for an external npm package (@lxgicstudios/mockapi), not a functional agent skill. The SKILL.md contains only installation instructions and usage documentation for a third-party CLI tool, with no actual agent instructions or executable code. This is deceptive packaging that misleads users about what they're installing.
SKILL.md:1
# MockAPI
Create a REST API from a JSON file...
## Installation
```bash
npm install -g @lxgicstudios/mockapi
```MEDIUM Potential Tool Exploitation via External Package Installation Unauthorized Tool Usellm
The skill instructs users to install an external npm package (@lxgicstudios/mockapi) globally without any version pinning, integrity checks, or security warnings. While the skill itself contains no executable code, it serves as a vector to get users to install and run arbitrary third-party code. The package could be compromised, typosquatted, or malicious. There's no verification of package authenticity or provenance.
SKILL.md
```bash
npm install -g @lxgicstudios/mockapi
```
No version specified, no integrity hash, no security warnings.LOW Missing Referenced File - Potential Hidden Payload Data Exfiltrationllm
The skill references a file 'a.py' in its instructions but this file is not found in the package. This could indicate: (1) incomplete packaging, (2) a removed malicious payload, or (3) an error in the skill structure. The presence of a Python file reference with no context is suspicious given the skill claims to be about an npm package.
Referenced Files: Files referenced in instructions: a.py
**Referenced File: a.py** (not found)What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 2.1 KB |
External hosts referenced
github.com lxgicstudios.com x.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/mockapi
- Raw scan result: mockapi-instant-rest-api-from-json-scan.json
- Badge for your README:
- Request a re-scan