error-handler-gen
3 findings (1 high, 2 medium), mainly social engineering, data exfiltration, unauthorized tool use. Most recent scan 2026-02-06.
This skill exhibits HIGH-risk deceptive practices. It masquerades as an error handler generator but contains no executable code - only documentation for an external npm package. This is social engineering through tool poisoning: the skill occupies namespace and discovery surface without providing actual functionality. The undisclosed OPENAI_API_KEY requirement creates credential exposure risk. The skill should either be removed or completely rewritten with actual implementation. Currently, it misleads users about its capabilities and dependencies while providing zero agent functionality.
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 error handling middleware for any framework. Use when setting up API error handling.
- Package
- 7 files, 36 KB
- SKILL.md
- 285 words, 12+ sections
- Code
- TypeScript (2)
SKILL.md covers: Error Handler Generator · Quick Start · What It Does · Usage Examples · Express middleware · Fastify in JavaScript · Next.js API routes · Koa · Best Practices · When to Use This · Part of the LXGIC Dev Toolkit · Requirements
Findings
HIGH Deceptive Skill Description - External Tool Masquerading as Agent Skill Social Engineeringllm
The skill claims to be an 'Error Handler Generator' for agent use, but the instructions exclusively describe an external npm package ('npx ai-error-handler') that requires Node.js and OPENAI_API_KEY. This is social engineering - the skill misleads users into believing it provides error handling generation capabilities when it actually just documents an external tool. The skill has no executable code, no actual functionality, and cannot perform the described operations. This is tool poisoning through deceptive metadata.
SKILL.md:1
Description claims 'Generate error handling middleware for any framework' but instructions only show 'npx ai-error-handler express' commands. No Python/Bash scripts exist to implement this functionality. The skill is a hollow wrapper around an external npm package.MEDIUM Undisclosed External Dependency with API Key Requirement Data Exfiltrationllm
The skill requires OPENAI_API_KEY environment variable but this is buried in the requirements section and not disclosed in the YAML manifest. This creates a credential exposure risk - users may not realize the skill (or the external tool it references) will access their OpenAI API key. The skill description makes no mention of OpenAI API usage or associated costs.
SKILL.md:50
'Needs OPENAI_API_KEY environment variable' appears only in requirements section. No disclosure in manifest description field. Users activating this skill may unknowingly expose API credentials to the external npm package.MEDIUM Tool Shadowing - No Actual Tool Implementation Unauthorized Tool Usellm
The skill name and description suggest it's a tool that generates error handlers, but it contains zero executable code. This is tool shadowing - it occupies the namespace and discovery surface for 'error-handler-gen' without providing any actual functionality. When an agent tries to use this skill, it will find only documentation for an external npm package, not working code.
SKILL.md:1
Manifest declares 'name: error-handler-gen' and 'description: Generate error handling middleware' but 'Script Files: No script files found'. The skill cannot execute its stated purpose.What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 642 B |
SKILL.md | doc | 2.0 KB |
package-lock.json | config | 30 KB |
package.json | config | 673 B |
tsconfig.json | config | 251 B |
src/cli.ts | script | 1.2 KB |
src/index.ts | script | 1021 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.
- 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/error-handler
- Raw scan result: error-handler-generator-scan.json
- Badge for your README:
- Request a re-scan