Ai Code Generator
v1.0.0AI code generator using Plan-and-Solve + ReAct for generating complete, runnable code from requirements and specifications.
⭐ 0· 39·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, SKILL.md, package.json, and index.js all align: the package provides a CodeGenerator class that asks an LLM to produce analyses, architecture, files, tests, and docs. There are no unrelated environment variables, binaries, or config paths requested.
Instruction Scope
SKILL.md and index.js focus on analyzing requirements and generating code artifacts. Instructions do not direct reading of host files, unusual system paths, or external endpoints beyond the implied LLM usage. The README/example usage is specific and bounded.
Install Mechanism
No install spec is provided; this is instruction+library-only. No downloads or archive extraction occur in the package files.
Credentials
The skill requests no env vars or credentials itself. However, it depends on an LLM implementation (this.llm.generate). That LLM — supplied by the runtime/agent — will likely call external LLM providers and therefore will transmit user-provided prompts/requirements externally. Users should be aware that prompts may include sensitive information and could be sent to whichever LLM backend the agent uses.
Persistence & Privilege
Skill does not request always:true, does not modify other skills or system configuration, and has no install-time persistence. It only returns generated files in-memory (it does not write to disk itself).
Assessment
This skill appears to do what it claims, but before installing consider: (1) Do not include secrets, private API keys, or proprietary code in prompts—generated prompts are sent to the LLM backend used by your agent. (2) Review all generated code and dependency manifests carefully for security issues and supply-chain risks before running or installing dependencies. (3) The package returns files in-memory; if you allow the agent to write files to disk automatically, ensure the agent is running in a safe environment (sandbox/isolated workspace). (4) If you want to limit data exposure, verify which LLM implementation your agent will use and its data-retention/privacy policy.Like a lobster shell, security has layers — review code before you run it.
latestvk971frzeeqrwry0q14r8kd66t1842bqy
License
MIT-0
Free to use, modify, and redistribute. No attribution required.