Add Discord bot channel integration via Chat SDK.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
After setup, the installed Discord adapter relays server messages (including any @mention of the bot from other server members) into the agent's workflow without the agent selecting a specific item, so outsiders who share a server with the bot can feed it free text.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The `nc:copy from-branch:channels` step fetches executable adapter and test code from a remote `channels` branch that is copied into `src/channels/` and then built and run. The branch is named without an explicit remote URL, and the NanoClaw project is the likely first-party publisher, but that is not independently established, so under recall-first I assign the common/reputable unofficial tier (medium).
nanocoai/nanoclaw
dad1aad
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.