← Back to Skills Marketplace
qwe
by
Phan Văn Năng
· GitHub ↗
· v1.0.0
· MIT-0
212
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install qwe
Description
Facebook Publisher Skill (Automate Page Posts via Graph API)
Usage Guidance
This skill largely does what it claims (posting to Facebook Pages), but there are several red flags you should address before running it: 1) config.validate() requires OPENAI_API_KEY and APIFY_API_TOKEN even though those services are unused — remove or understand why they are required. 2) The token helper explicitly tells you to pick a specific App ID in Graph Explorer (4348763312075291) — do not use someone else's app; generate tokens with your own app and app secret. 3) The helper prints long-lived tokens to the console and writes them to fb_tokens_output.json; remove printing and file writes or ensure you run in an isolated environment and never commit saved token files. 4) If you plan to run these scripts, run them in an isolated VM/container, review and remove any hardcoded sample values, and avoid pasting production secrets until you confirm the code has been cleaned. Given these issues, proceed only after code cleanup or further verification.
Capability Analysis
Type: OpenClaw Skill
Name: qwe
Version: 1.0.0
The skill bundle is a functional toolset designed to automate Facebook Page posts via the Graph API. It includes scripts for token management (fb_token_helper.py), media uploads, and post scheduling (fb_publisher_agent.py). While the bundle handles sensitive credentials and stores them in a local file (fb_tokens_output.json) for user convenience, this behavior is documented and aligned with the stated purpose. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
The SKILL.md and code implement Facebook Page posting and token exchange, which matches the declared purpose. However config.py's validate() lists unrelated required env vars (OPENAI_API_KEY and APIFY_API_TOKEN) in addition to Facebook vars. Those services (OpenAI, Apify) are not used anywhere else in the shipped scripts, so requiring them is disproportionate and incoherent with a pure FB publisher skill.
Instruction Scope
SKILL.md instructs interactive token flow and running provided scripts, which aligns with the code. But agents/fb_token_helper.py instructs users to select a specific App ID (4348763312075291) in Graph Explorer — this encourages using an app that may not be the user's and is a red flag. The helper prints long-lived tokens to the console and writes them to a local JSON file (fb_tokens_output.json), contradicting the SKILL.md's own 'Never log tokens' guidance and increasing leak risk.
Install Mechanism
No install spec; this is an instruction-and-code-only skill. Nothing is downloaded or installed automatically, which lowers supply-chain risk.
Credentials
SKILL.md declares FB_APP_ID, FB_APP_SECRET, FB_PAGE_ID, FB_PAGE_ACCESS_TOKEN which are appropriate. But config.py also reads many other env vars (OPENAI_API_KEY, APIFY_API_TOKEN, FB_CLIENT_TOKEN, FB_USER_ACCESS_TOKEN) and its validate() will raise if OPENAI_API_KEY and APIFY_API_TOKEN are not set — these appear unrelated to Facebook posting and are disproportionate. The skill asks users to paste tokens interactively and then prints/saves them, which is unnecessary exposure of secrets.
Persistence & Privilege
The skill does not request special platform privileges and always:false. However fb_token_helper.py persists tokens to fb_tokens_output.json and suggests storing tokens in .env; both create local persistence that can be accidentally committed or accessed by other processes. The skill does not modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qwe - After installation, invoke the skill by name or use
/qwe - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
qsadasd
Metadata
Frequently Asked Questions
What is qwe?
Facebook Publisher Skill (Automate Page Posts via Graph API). It is an AI Agent Skill for Claude Code / OpenClaw, with 212 downloads so far.
How do I install qwe?
Run "/install qwe" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is qwe free?
Yes, qwe is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does qwe support?
qwe is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created qwe?
It is built and maintained by Phan Văn Năng (@yunneetoichoi); the current version is v1.0.0.
More Skills