Slack Integration
Analysis
This Slack skill is purpose-aligned, but it gives an agent broad Slack read/write authority that can post, update, upload, and manage workspace content without clear approval boundaries.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
curl -s -X POST https://slack.com/api/chat.postMessage ... chat.update ... chat.scheduleMessage ... conversations.create ... conversations.setTopic ... files.remote.add
The skill provides raw Slack Web API commands that can publish, modify, schedule, create channels, change topics, and share files in a workspace. The artifact does not pair these high-impact write actions with explicit approval, channel scoping, or review guidance.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Works with bot tokens or user tokens. ... Bot Token Scopes: chat:write, channels:read, channels:history, files:write, reactions:write, users:read ... For user-level actions ... use a User OAuth Token (`xoxp-...`) instead.
The documented token scopes allow the agent to read Slack channels and users and perform workspace write actions; user tokens can also act with a user's delegated authority. This is sensitive, high-impact account access.
