Law
v1.0.0Support legal understanding from everyday rights to professional practice and scholarship.
⭐ 3· 1.6k·9 current·9 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description ('Law') match the SKILL.md content: it provides information and teaching across user types (public, students, attorneys, researchers, paralegals). No unrelated binaries, environment variables, or config paths are requested.
Instruction Scope
Runtime instructions stay within legal information/education and explicitly prohibit giving legal advice and request jurisdiction/clarification from users. They do ask the agent to cite primary sources and apply professional formats (Bluebook/OSCOLA), but give no mechanism for fetching/verifying citations — this increases the risk of hallucinated or stale citations (accuracy risk, not a secret-exfiltration risk). The SKILL.md does not instruct reading system files, env vars, or sending data to external endpoints.
Install Mechanism
No install spec or code files are provided (instruction-only), so nothing will be written to disk or downloaded during installation.
Credentials
The skill declares no required environment variables, credentials, or config paths. It does not request access to unrelated services or secrets.
Persistence & Privilege
Flags are normal: always is false and the skill is user-invocable. The skill does not request permanent presence or elevated platform privileges.
Assessment
This skill is internally consistent and doesn't ask for credentials or install code, but it is only a set of instructions for how the agent should behave. Before relying on outputs: (1) remember the skill explicitly says it should not give legal advice — treat answers as informational only; (2) verify any cited statutes/cases and their dates/authority yourself (the skill asks for citations but provides no built-in verification, so hallucinated or outdated citations are possible); (3) avoid pasting confidential or privileged facts into the chat (the skill warns about privilege concerns but cannot enforce confidentiality); and (4) if you need binding legal advice or representation, consult a licensed attorney in the relevant jurisdiction. If you prefer the agent not to call this skill autonomously, consider disabling autonomous invocation in your agent settings.Like a lobster shell, security has layers — review code before you run it.
latestvk972123vfqg3g0864b3d59rx2980x59p
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
⚖️ Clawdis
OSLinux · macOS · Windows
