landing-gen
Verdict safe, but 2 findings (2 medium), mainly social engineering, unauthorized tool use. Most recent scan 2026-02-06.
This skill package has significant structural issues. It appears to be documentation for an external npm package ('ai-landing') rather than a functional agent skill. The package lacks agent instructions, references a missing script file (description.py), and has incomplete manifest metadata. While no active malicious behavior is detected (no data exfiltration, command injection, or prompt injection), the misleading presentation and broken dependencies create moderate security and functionality concerns. The skill cannot function as described and may confuse users about its actual capabilities. Primary issues are deceptive packaging (presenting external tool docs as an agent skill) and missing dependencies.
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
Generate landing page code from product descriptions
- Package
- 1 file, 1.2 KB
- SKILL.md
- 156 words, 11 sections
- Code
- None. Instructions only.
SKILL.md covers: Landing Page Generator · Quick Start · What It Does · Usage Examples · Generate from description · Specify sections · Choose style · Output Includes · Sections Generated · Requirements · License
Findings
MEDIUM Misleading Skill Description - External Tool Masquerading as Agent Skill Social Engineeringllm
The skill presents itself as an agent skill package but actually describes an external npm package ('npx ai-landing'). The SKILL.md contains no agent instructions, only documentation for a separate command-line tool. This is deceptive because users expect agent skills to provide instructions the agent follows, not documentation for external tools. The skill cannot function as described since it requires 'npx' execution and OPENAI_API_KEY, which are not part of the agent skill framework.
Quick Start section shows 'npx ai-landing' commands, Requirements mention 'Node.js 18+' and 'OPENAI_API_KEY required', but no agent instructions are provided for how the agent should use this skill.MEDIUM Missing Referenced Script File Unauthorized Tool Usellm
The skill references 'description.py' in its instructions but this file is not included in the skill package. This creates a broken dependency that prevents the skill from functioning. If description.py was intended to contain malicious code, its absence prevents detection. If it's a legitimate component, the skill is incomplete and non-functional.
Referenced Files section shows 'description.py (not found)'. The file is mentioned but not provided in the package.What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 1.2 KB |
External hosts referenced
github.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/ai-landing
- Raw scan result: landing-page-generator-scan.json
- Badge for your README:
- Request a re-scan