domain-name-brainstormer
Verdict safe, but 1 finding (1 medium), mainly social engineering. Most recent scan 2026-02-06.
This skill is a domain name brainstorming tool with MODERATE security concerns primarily related to misleading capability claims rather than active security threats. The skill claims to check domain availability across multiple TLDs but provides no implementation to actually perform this verification - no scripts, no API calls, no WHOIS lookups. This constitutes social engineering through deceptive descriptions (AITech-2.1). The skill would generate fictional availability data, potentially misleading users. However, there are NO active security threats like data exfiltration, prompt injection, command injection, or credential theft. The skill is essentially a text generation template without executable code. The missing optional metadata fields (license, compatibility, allowed-tools) reduce transparency but are low severity. Primary recommendation: Either implement actual domain checking functionality or rebrand as an 'idea generator' without availability claims.
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
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
- Package
- 2 files, 9.6 KB
- SKILL.md
- 818 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: Domain Name Brainstormer · When to Use This Skill · What This Skill Does · How to Use · Basic Brainstorming · Specific Preferences · With Keywords · Example · Available (.com) · Available (Alternative TLDs) · Premium/Taken (.com) · Recommendations
Findings
MEDIUM Misleading Capability Claims - Domain Availability Checking Not Implemented Social Engineeringllm
The skill description and instructions claim to 'check availability across multiple TLDs' and 'verifies which domains are actually available', but no implementation exists. The skill contains no Python/Bash scripts to perform actual domain availability checks via WHOIS, DNS queries, or domain registrar APIs. The example output shows 'Available' status markers (✓) implying real availability verification, but this is deceptive - the agent would only be generating fictional availability data without actual verification capability.
SKILL.md
Description claims: 'checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.)' and 'Verifies which domains are actually available'. Example output shows '✓ snippetbox.com - Clear, memorable, available!' but no scripts exist to perform this verification.What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 4.1 KB |
SKILL.md | doc | 5.6 KB |
Package contents recorded 2026-10-22 at commit b00cf8491de1. 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://github.com/softaworks/agent-toolkit
- Raw scan result: domain-name-brainstormer-scan.json
- Badge for your README:
- Request a re-scan