webhook-gen
Verdict safe, but 2 findings (2 medium), mainly social engineering. Most recent scan 2026-02-07.
This skill package has MEDIUM severity issues primarily related to deceptive presentation. The skill masquerades as an agent capability but actually describes an external npm CLI tool ('npx ai-webhook'), making it misleading to users who expect agent skills to extend the AI assistant's direct capabilities. The package contains no executable scripts (Python/Bash) and instead provides documentation for a Node.js command-line tool. Additionally, the skill includes promotional content for LXGIC Studios' developer toolkit, which is inappropriate for agent skill packages. While there are no critical security threats like data exfiltration or command injection (since there's no executable code), the deceptive nature of the skill description and the promotional content constitute social engineering concerns. The skill also has minor issues with missing referenced files and incomplete metadata. This appears to be either a misunderstanding of what agent skills are, or an attempt to use the agent skills ecosystem for promotional purposes rather than providing genuine agent capabilities.
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 webhook handlers with retry logic using AI. Use when integrating Stripe, GitHub, or any webhook provider.
- Package
- 7 files, 36 KB
- SKILL.md
- 340 words, 12+ sections
- Code
- TypeScript (2)
SKILL.md covers: Webhook Generator · Quick Start · What It Does · Usage Examples · Stripe payment webhook · GitHub push events · Generic webhook with retry · Specify provider explicitly · TypeScript output · Best Practices · When to Use This · Part of the LXGIC Dev Toolkit
Findings
MEDIUM Deceptive Skill Description - External Tool Masquerading as Agent Skill Social Engineeringllm
The skill description and instructions describe an external npm package ('npx ai-webhook') rather than an agent skill that the AI assistant can execute. The entire SKILL.md contains instructions for a command-line tool that requires Node.js and npm, not instructions for the agent to follow. This is misleading because users expect agent skills to extend the agent's capabilities directly, not to be documentation for external tools. The skill appears to be promotional content for LXGIC Studios' developer toolkit rather than a functional agent skill.
SKILL.md
Quick Start section shows 'npx ai-webhook "stripe payment succeeded"' - this is an external npm command, not an agent capability. The entire document describes CLI usage patterns, npm installation, and external tool features rather than agent instructions.MEDIUM Promotional Content Disguised as Functional Skill Social Engineeringllm
The skill contains extensive promotional content for LXGIC Studios ('Part of the LXGIC Dev Toolkit', 'This is one of 110+ free developer tools built by LXGIC Studios', links to GitHub, Twitter, Substack, website). This promotional material is embedded within what appears to be a functional skill description, which is misleading. Agent skills should focus on providing capabilities to the agent, not serving as advertisement platforms.
SKILL.md
Section titled 'Part of the LXGIC Dev Toolkit' contains: 'This is one of 110+ free developer tools built by LXGIC Studios. No paywalls, no sign-ups, no API keys on free tiers. Just tools that work.' followed by multiple promotional links.What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 666 B |
SKILL.md | doc | 2.5 KB |
package-lock.json | config | 30 KB |
package.json | config | 642 B |
tsconfig.json | config | 251 B |
src/cli.ts | script | 1.1 KB |
src/index.ts | script | 942 B |
External hosts referenced
registry.npmjs.org github.com feross.org www.patreon.com lxgic.dev lxgicstudios.substack.com paypal.me 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.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- 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/webhook-gen
- Raw scan result: webhook-generator-scan.json
- Badge for your README:
- Request a re-scan