Security audit
Security checks for vulnerabilities and agentic risk
This Slack skill is a disclosed control wrapper for Clawdbot Slack actions, with sensitive capabilities that users should scope carefully but no hidden or malicious behavior in the artifact.
Install only if you intend Clawdbot to act in Slack. Before use, confirm the bot token has least-privilege Slack scopes, restrict it to appropriate channels, and treat message reads, message deletion/editing, DMs, and member lookups as access to potentially sensitive workplace data.
The skill allows reading recent messages and fetching member information using a bot token, but it does not disclose the privacy implications or advise on least-privilege usage. Without explicit warnings, users may unknowingly expose private channel content or personal profile information to agent workflows that aggregate, summarize, or retransmit data beyond the original Slack context.
The skill allows reading recent messages and fetching member information using a bot token, but it does not disclose the privacy implications or advise on least-privilege usage. Without explicit warnings, users may unknowingly expose private channel content or personal profile information to agent workflows that aggregate, summarize, or retransmit data beyond the original Slack context.
The manifest description focuses on 'reacting to messages or pinning/unpinning items,' which suggests a relatively narrow control surface. However, the skill documentation also exposes sending, editing, deleting, and reading messages, plus fetching member info and listing custom emoji, which materially broadens the behavior beyond the manifest summary.
No suspicious patterns detected.
