Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
StockScanner Pro
v1.0.0社交媒体自动化运营助手。自动生成并发布小红书、微博、Twitter 内容，定时发送、互动回复。
⭐ 0· 75·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description match a social-posting tool and the SKILL.md explains the need for platform credentials (Twitter keys, Weibo token, Xiaohongshu cookie) and a license_key. However the registry metadata declares no required env vars or config paths, creating a mismatch between the declared package surface and the documented runtime requirements.
Instruction Scope
SKILL.md instructs the user/agent to add credentials and license_key to ~/.openclaw/openclaw.json and to schedule cron jobs. That means the skill expects to read/write user configuration and persist task data. The instructions are explicit about storing secrets in a local config file, but the runtime instructions do not declare or limit what the agent should do with those secrets. Additionally the README/cron examples encourage installation into the user's home directory which grants the skill persistent local storage.
Install Mechanism
There is no install spec; this is instruction + small bundled script only. That is low risk from an installation/remote-download perspective — nothing is pulled from external URLs during install.
Credentials
While the skill legitimately needs platform credentials to post, those credentials are only described in SKILL.md (config file), not declared in the registry metadata. The primaryEnv/required env/config fields are empty, which is inconsistent. The SKILL.md asks users to place secrets (license_key, API keys, cookies, tokens) into a local config file; that is proportionate to purpose but should have been declared explicitly. This mismatch reduces transparency and is a potential red flag.
Persistence & Privilege
The skill is not always:true and does not request elevated system-wide privileges. It writes its own tasks.json under ~/.openclaw/workspace/skills/socialpost-auto/data, which is expected for a scheduler. It does not modify other skills or global agent settings.
What to consider before installing
This package looks like a half-implemented social-posting assistant: the docs tell you to store platform credentials and a license_key in ~/.openclaw/openclaw.json, but the registry metadata does not declare those requirements and the included scripts are stubs that only print actions rather than actually calling platform APIs. Before installing or putting real secrets into your OpenClaw config: (1) inspect or run the code in a sandbox to confirm where credentials are read and whether they're transmitted to any external endpoints; (2) prefer creating limited-scope API tokens (not full account passwords) and avoid storing more-privileged secrets in the config until you verify behavior; (3) if you need full posting functionality, ask the author for a clear manifest of required credentials and for the code to be completed or for a vetted release; (4) if you see unexpected network calls (to domains other than official platform APIs) or code that exfiltrates data, do not use it and remove stored secrets. Additional info that would lower suspicion: updated metadata declaring the config path/required creds, and an implementation that clearly uses only the official platform APIs (or documented OAuth flows) with no external exfiltration.Like a lobster shell, security has layers — review code before you run it.
a-sharesvk97c75f0ng4yyy0g4h270hmm5d84kgmealertvk97c75f0ng4yyy0g4h270hmm5d84kgmelatestvk97c75f0ng4yyy0g4h270hmm5d84kgmescannervk97c75f0ng4yyy0g4h270hmm5d84kgmestockvk97c75f0ng4yyy0g4h270hmm5d84kgmetechnical-analysisvk97c75f0ng4yyy0g4h270hmm5d84kgme
License
MIT-0
Free to use, modify, and redistribute. No attribution required.