codemod-gen
3 findings (2 high, 1 medium), mainly data exfiltration, unauthorized tool use, social engineering. Most recent scan 2026-02-05.
This skill presents MODERATE TO HIGH security risks. The primary concerns are: (1) requiring users to expose OPENAI_API_KEY to unvetted third-party code executed via npx, (2) no supply chain security (unpinned package versions, no integrity checks), and (3) misleading simplicity claims that obscure security prerequisites. The skill delegates all functionality to an external npm package (ai-codemod) without providing transparency about what that package does with user credentials or code. While the core concept (codemod generation) is legitimate, the implementation creates credential exposure and supply chain attack vectors. The skill would benefit from either implementing codemod generation locally or providing much stronger security guidance and package verification steps.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco rates this HIGH and SkillSpector found nothing. Check the false-positive register; signature matches on documentation are the usual cause. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Generate codemods for large-scale code changes. Use when refactoring patterns across many files.
- Package
- 1 file, 2.4 KB
- SKILL.md
- 333 words, 12+ sections
- Code
- None. Instructions only.
SKILL.md covers: Codemod Generator · Quick Start · What It Does · Usage Examples · Class to functional components · Modernize code · API migrations · Framework upgrades · Best Practices · When to Use This · Part of the LXGIC Dev Toolkit · Requirements
Findings
HIGH Hardcoded External API Key Requirement Data Exfiltrationllm
The skill requires users to set an OPENAI_API_KEY environment variable to function. This creates a credential exposure risk as the skill executes an external npx command that will access this API key. Users may unknowingly expose their OpenAI credentials to third-party code they haven't audited. The skill provides no transparency about how this key is used or transmitted.
SKILL.md
Requirements section states: 'Needs OPENAI_API_KEY environment variable' and 'npx ai-codemod' command will access this credentialHIGH Unvetted Third-Party Code Execution via npx Unauthorized Tool Usellm
The skill instructs users to execute 'npx ai-codemod' which downloads and runs arbitrary code from npm without any version pinning, integrity checks, or security verification. This is a supply chain attack vector - the package could be compromised, typosquatted, or malicious. Users are instructed to run this with their OPENAI_API_KEY exposed in the environment.
SKILL.md
Quick Start section: 'npx ai-codemod "convert class components to functional"' - no version specified, no integrity hash, no security verificationMEDIUM Misleading Simplicity Claims Social Engineeringllm
The skill claims 'Zero config. Just works' and 'No install needed' but actually requires Node.js 18+, OPENAI_API_KEY environment variable setup, and npx availability. This social engineering through oversimplification could lead users to run the tool without understanding the prerequisites or security implications.
SKILL.md
Claims 'One command. Zero config. Just works' but Requirements section reveals: 'Node.js 18+ recommended. Needs OPENAI_API_KEY environment variable'What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 2.4 KB |
External hosts referenced
github.com x.com lxgicstudios.com lxgicstudios.substack.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-codemod
- Raw scan result: codemod-generator-scan.json
- Badge for your README:
- Request a re-scan