Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Discord Hub My
v1.0.2OpenClaw skill for Discord Bot API workflows, covering interactions, commands, messages, and operations using direct HTTPS requests.
⭐ 0· 1.5k·5 current·6 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill describes Discord Bot API workflows (bot tokens, interaction public key, application ID) and REST request templates — that purpose is plausible. However the included scripts implement only a simple webhook sender (requires WEBHOOK_URL), and the registry metadata lists no required env vars or primary credential. There is thus a mismatch between the stated capability (full bot operations using tokens) and the actual code (webhook-only).
Instruction Scope
SKILL.md instructs the agent/operator to provide bot tokens, application ID, and interaction public key and references signature verification and rate-limit handling, but the runtime files do not implement those behaviors. The run.sh sources a .env file from the skill directory (it will load any environment variables placed there). The instructions give broad guidance but do not match the code, granting the agent/operator ambiguous discretion about where/how to supply secrets.
Install Mechanism
No install spec; this is instruction-only with two small shell scripts. Nothing is downloaded or written by an installer, which minimizes install-time risk.
Credentials
Registry metadata declares no required env vars, yet SKILL.md asks for sensitive credentials (bot token, application ID, interaction public key). The actual scripts expect WEBHOOK_URL (not declared). run.sh auto-sources a local .env, which could cause accidental loading of unrelated secrets if a user drops a .env containing other credentials into the skill folder. The mismatch between declared requirements and actual env usage is a red flag.
Persistence & Privilege
always is false and there is no install; the skill does not request persistent system privileges or modify other skills. It only contains small scripts that execute when run.
What to consider before installing
This package is inconsistent: the README asks for bot tokens and interaction keys but the code only uses a WEBHOOK_URL and sources a local .env. Before installing or running: 1) Ask the publisher to clarify which credentials are actually required and to declare them in registry metadata. 2) Inspect any .env file you might place in the skill directory — do not reuse a file that contains unrelated secrets. 3) If you only need webhook posting, prefer supplying a dedicated webhook URL with least privileges; do not supply your Bot token unless the skill explicitly needs and documents how it will be used. 4) Run the scripts in a sandboxed environment (or review/modify them) to ensure they don't load unexpected secrets or call remote endpoints you don't control. 5) Note the metadata/manifest inconsistencies (ownerId/slug differences) and prefer skills with clear provenance. If the author cannot explain the mismatches, treat the package with caution or avoid installing it.Like a lobster shell, security has layers — review code before you run it.
latestvk97ck82sh4azt9rf459a7s19y580ntat
License
MIT-0
Free to use, modify, and redistribute. No attribution required.