Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Rule Spec
v1.0.5Define, manage, and compile business rules as structured YAML data into LLM-ready prompts and agent-loadable SKILL.md files. Use when the user wants to creat...
⭐ 0· 0·0 current·0 all-time
byRic@pallaoro
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md's behavior (compiling rules into SKILL.md files that agents then load) is consistent with the stated purpose, but the manifest declares no required binaries while the instructions require 'npx' (npm) at runtime. Also, generating files under skills/{domain}/SKILL.md means the skill can create or modify other agent skills — a more privileged action than a simple rule-authoring tool and worth explicit justification.
Instruction Scope
The instructions direct the agent (or user) to run 'npx rulespec', which will fetch and execute code from the npm registry at runtime, and to emit SKILL.md into the agent's skills directory. That combines remote code execution (via npx) with writing agent-loadable skill files, which could be used to change agent behavior. The SKILL.md does not require human review of emitted files before agents load them.
Install Mechanism
There is no install spec in the registry metadata, but the doc explicitly relies on 'npx rulespec' which downloads an npm package at runtime. Using npx implies a remote install/execute step (npm) and therefore supply‑chain risk; the manifest doesn't name or verify the package source or required binary (npx/npm).
Credentials
The skill requests no environment variables, credentials, or config paths in the manifest, which is appropriate for a rule-authoring tool. However, it does instruct writing into a skills/ path (agent configuration area) — this is more about persistence/privilege than environment secrets.
Persistence & Privilege
The workflow explicitly emits SKILL.md into skills/{domain}/SKILL.md and states agents will load those files. That means using the tool can create or modify agent skills (changing agent capabilities). Although always:false (not force-included), this write-to-skills behavior is a high-privilege action and should be controlled (human review, restricted output dir, or sandboxing).
What to consider before installing
Before installing or using this skill: 1) Ask the publisher for the official npm package name, homepage, and the source code repo so you can inspect the 'rulespec' package that npx will fetch. 2) Note that the SKILL.md relies on npx/npm but the manifest doesn't declare that dependency — ensure npx will be coming from a trusted environment. 3) Be cautious: the tool emits SKILL.md files into skills/{domain}, which can change what agents load; require a manual review step (or sandbox) before any emitted SKILL.md is loaded into production agents. 4) Prefer to run 'npx rulespec' manually or in an isolated environment first, audit the generated SKILL.md, and examine the rulespec package code for malicious behavior. 5) If you must allow automated runs, restrict the output directory (do not write into the live skills/ folder), enforce human approval for emitted SKILL.md, or request an install spec that pins a vetted release from a known repository. These mitigations reduce supply‑chain and privilege risks.Like a lobster shell, security has layers — review code before you run it.
latestvk97adbnfantzcn9xshwqt3gtv184k65r
License
MIT-0
Free to use, modify, and redistribute. No attribution required.