Load to bind an overseer's mailbox to a private Slack channel, run or check the relay, or post an alert or a file to Slack.
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/slack/SKILL.mdThe skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill tells the agent to run `slack install`, which writes and restarts a service unit, and to run `slack setup`, which restarts that unit, but it never mentions sudo or system-wide paths, so the machine-state impact is real but limited and not clearly privileged.
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.
The required relay monitors a private Slack channel that any non-owner member can post into (socket events and history catch-up), and its parent pointers carry the first 300 characters of a thread root labelled `owner` for any non-bot author, so outsider text reaches the overseer as directive context.
vanillagreencom/kendex
3a2f84c
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.