Legal Matter Intake Summarizer
v1.0.0把法律相关咨询材料整理成事实、争议点、缺失材料与后续问题，不给法律结论。；use for legal, intake, case-summary workflows；do not use for 提供法律意见结论, 替代律师审查.
⭐ 0· 97·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (legal intake summarizer) match the included files and script. The only required binary is python3, there are no unrelated credentials, and resources (spec.json, template.md) drive generation — all proportional to a local summarizer/audit tool.
Instruction Scope
SKILL.md confines behavior to producing structured summaries and explicitly forbids performing external system changes. The script supports reading files and directories and will scan many text file types (md, txt, json, py, js, sh, csv, etc.) and produce reports. This file-read capability is appropriate for a local audit/summarizer, but users should avoid supplying system-sensitive paths (e.g., /home, /etc, credential stores) as input.
Install Mechanism
No install spec; this is instruction-only plus a local python script. No downloads or third-party package installs are requested.
Credentials
The skill requests no environment variables or credentials. The included script scans local files but does not access remote endpoints or require secrets, so requested environment access is proportional to purpose.
Persistence & Privilege
always is false and the skill is user-invocable. It does not attempt to modify other skills or system-wide agent settings. Note: autonomous invocation is allowed (disable-model-invocation=false) — normal for skills — so users should consider whether they want the agent to run this skill without confirmation.
Scan Findings in Context
[curl_pipe_bash] expected: The script contains a regex to detect 'curl | bash' patterns; this is a scanner to identify dangerous snippets in input files and is appropriate for an audit tool.
[dangerous_rm] expected: The script looks for 'rm -rf' patterns to flag risky commands in scanned files; this is expected for a local pattern-audit feature.
[base64_exec] expected: Detecting base64-decoded execution patterns is part of the script's high-risk pattern matching; appropriate for the skill's auditing purpose.
[secret_like] expected: The script searches for secret-like tokens in files (and masks part of them when reporting). This is expected for an intake/audit helper to surface potential PII/credentials.
[private_url] expected: Detects private/admin URLs in scanned content; appropriate as part of pattern scanning for risky items.
Assessment
This skill appears coherent and safe for local, read-only summarization of case materials. Before running it: (1) only provide the specific input files or a dedicated directory — do not point it at system or home directories containing secrets, credentials, or unrelated data; (2) prefer a sandbox or isolated workspace if processing potentially sensitive PII; (3) review generated output before acting on it — the skill intentionally avoids giving legal conclusions; (4) be mindful that the agent can invoke the skill autonomously by default — if you do not want unattended runs, disable autonomous invocation at the agent level or require explicit user confirmation.Like a lobster shell, security has layers — review code before you run it.
latestvk979p64xqpe3g8vahgc8a0jy858358jp
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
⚖️ Clawdis
OSmacOS · Linux · Windows
Binspython3