Discord
v1.0.1Use when you need to control Discord from Clawdbot via the discord tool: send messages, react, post or upload stickers, upload emojis, run polls, manage threads/pins/search, fetch permissions or member/role/channel info, or handle moderation actions in Discord DMs or channels.
⭐ 65· 30.2k·1.2k current·1.2k all-time
byPeter Steinberger@steipete
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skill's stated purpose is legitimate (control Discord via a bot), but the manifest lists no primary credential or required env vars while the instructions explicitly say 'The tool uses the bot token configured for Clawdbot.' That missing declaration is an incoherence. Also the skill has no source/homepage and an unknown owner, reducing traceability.
Instruction Scope
The SKILL.md permits reading recent messages, performing moderation, and uploading media via file:///local paths. Allowing local file:/// uploads means the agent may access arbitrary local files to send to remote Discord — this expands the scope beyond simple API calls and could lead to unintended data exfiltration if not restricted. The instructions otherwise stay within Discord functionality, and moderation actions are gated disabled-by-default.
Install Mechanism
Instruction-only skill with no install steps or code files — low install risk (nothing will be written to disk by an installer).
Credentials
No env vars or primary credential are declared, but the README explicitly references a bot token. The skill also implies access to local file paths for uploads. The manifest should declare the credential(s) it needs (e.g., DISCORD_BOT_TOKEN or equivalent) and document any filesystem access requirements—absence of that is disproportionate or sloppy.
Persistence & Privilege
always:false and normal model invocation are used (agent can be invoked autonomously, which is typical). The skill does not request system-wide persistence or modifications to other skills. The combination of autonomous invocation plus broad Discord actions is notable but not a manifest-specific privilege escalation.
What to consider before installing
This skill appears to implement Discord bot functionality, but there are coherence issues you should resolve before installing: 1) Require the author to declare the credential the skill uses (e.g., DISCORD_BOT_TOKEN or PRIMARY_DISCORD_TOKEN) in the manifest so you can audit and control where that token is stored. 2) Ask how file:/// uploads are intended to work and restrict uploads to a safe, explicit directory (or disallow local-file uploads) to avoid accidental exfiltration of sensitive files. 3) Verify the skill author/owner and request a source or homepage and, if possible, the exact implementation of the 'discord' tool the SKILL.md refers to. 4) Keep moderation/role-changing actions disabled by default (they already are) and consider requiring human approval for any moderation or role changes. 5) If you lack full trust in the author, run the skill only in a sandboxed environment or require explicit model-invocation approvals. If the author cannot clarify the missing credential and file-access behavior, treat this skill as unsafe to enable in production.Like a lobster shell, security has layers — review code before you run it.
latestvk979r9etqg0j4r5j3jxhnepczn7ym8ek
License
MIT-0
Free to use, modify, and redistribute. No attribution required.