Ezer Multi-Agent Report Auditor

v1.0.0

Wrapper skill for the Ezer audit backend API. Use this skill when the user asks to run a financial audit task by code/period/year/lang and return structured...

0· 139·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for mx-222/ezer-multiagent-auditor.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Ezer Multi-Agent Report Auditor" (mx-222/ezer-multiagent-auditor) from ClawHub.
Skill page: https://clawhub.ai/mx-222/ezer-multiagent-auditor
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: EZER_API_BASE_URL
Required binaries: python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install ezer-multiagent-auditor

ClawHub CLI

Package manager switcher

npx clawhub@latest install ezer-multiagent-auditor
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the actual behavior: the script POSTs to /api/tasks and polls /api/tasks/{id}/result. Declared requirements (python3, EZER_API_BASE_URL) are exactly what the script needs.
Instruction Scope
SKILL.md instructs running the included Python script with the expected arguments and environment variable. The instructions and script only perform HTTP calls to the configured EZER_API_BASE_URL and do not read other files, system paths, or unrelated environment variables.
Install Mechanism
No install spec; the skill is instruction-only plus a small included script. Nothing is downloaded or extracted at install time. Required runtime binary is only python3, which is reasonable.
Credentials
Only EZER_API_BASE_URL is required and EZER_BEARER_TOKEN is optional. These are proportionate for an API wrapper. No unrelated secrets or many environment variables are requested.
Persistence & Privilege
always:false and default invocation behavior are set. The skill does not request persistent system privileges or modify other skills/config; it only makes outbound HTTP requests to the configured base URL.
Assessment
This skill appears to do exactly what it claims, but review these operational cautions before enabling it: 1) Ensure EZER_API_BASE_URL points to a trusted Ezer backend (prefer HTTPS) — the script will make network requests to whatever you set, including internal network addresses. 2) Only provide EZER_BEARER_TOKEN if necessary and treat it as a secret with least privilege; rotate it if exposed. 3) The script prints the full JSON response to stdout which may include sensitive data — consider where the output will be stored or forwarded. 4) If you need stronger isolation, run the skill in a restricted environment or network namespace. The included Python source is small and readable; review it yourself if you want to confirm there is no additional data exfiltration beyond contacting the configured API endpoints.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

Binspython3
EnvEZER_API_BASE_URL
latestvk9796wm5dkzgh3r58dxk84gf4x83get1
139downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

Ezer Audit API Skill

This skill wraps the existing Ezer backend API and returns task result payloads.

When to use

Use this skill when the user wants to run an Ezer audit task with these fields:

  • code (example: 300750.SZ)
  • period (FY|Q1|Q2|Q3|H1)
  • year (integer)
  • lang (example: zh-CN)

Required environment

  • EZER_API_BASE_URL example: http://127.0.0.1:8008
  • EZER_BEARER_TOKEN optional if API auth is disabled

Run command

python3 {baseDir}/scripts/invoke_ezer_api.py \
  --code 300750.SZ \
  --period FY \
  --year 2021 \
  --lang zh-CN

Behavior

  1. POST /api/tasks to create task.
  2. Poll /api/tasks/{task_id}/result until completion or timeout.
  3. Print final JSON payload to stdout.

Notes

  • This skill does not expose any model-provider keys.
  • If the API returns failure, pass through error payload and non-zero exit.

Comments

Loading comments...