Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly coherent for managing OpenClaw agents and Discord channels, but it grants broad operational control over agents, gateway configuration, Discord channels, workspace files, and scheduled/background activity without consistently requiring explicit confirmation or scoping.
Install only if you intend to let this skill administer OpenClaw agents and Discord channels. Before running its workflows, confirm exact workspace paths, channel IDs, gateway patches, cron jobs, and spawned agent sessions, and prefer previews or backups before any rename, config patch, or workspace-wide update.
This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.
### Finding Discord IDs
**Enable Developer Mode:**
- Settings → Advanced → Developer Mode
**Copy IDs:**
Instructions found that direct the agent to transmit conversation context or user data to external services.
})
### Send Messages to Agents
**Direct communication:**
```typescript
Instructions found that direct the agent to transmit conversation context or user data to external services.
**4. Agent-to-agent communication:**
Agents can send messages to each other:
```typescript
// In Watson's context
sessions_send({
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
1. **Organize channels in categories** - Group related agent channels
2. **Use descriptive channel names** - Clear purpose from the name
3. **Set specific system prompts** - Give each channel clear context
4. **Document agent responsibilities** - Keep SOUL.md updated
5. **Set up memory cron jobs** - For agents with ongoing work
6. **Test agents individually** - Before integrating into team
The skill description says it is a 'complete toolkit' to use when setting up multi-agent systems, creating agents, or managing Discord channels, which is broad enough to trigger in many ordinary administrative requests. That increases the chance an agent will invoke a high-impact skill in contexts where the user did not explicitly request filesystem, gateway, or Discord changes.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
- **Emoji** (e.g., "🔬")
- **Specialty** (what the agent does)
- **Model** (which LLM to use)
- **Workspace** (where to create agent files)
- **Discord channel ID** (optional)
#### 2. Run Creation Script
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
- **Emoji** (e.g., "🔬")
- **Specialty** (what the agent does)
- **Model** (which LLM to use)
- **Workspace** (where to create agent files)
- **Discord channel ID** (optional)
#### 2. Run Creation Script
This section instructs the operator to run scripts that can create or modify Discord channels, patch gateway configuration, and potentially alter local workspace files, but it does not foreground the operational consequences or require explicit confirmation. In an agent setting, documentation like this can normalize destructive or externally visible actions without adequate user awareness.
Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.
## Requirements
**Bot Permissions:**
- `Manage Channels` - To create/rename channels
- `View Channels` - To read channel list
- `Send Messages` - To post in channels
No suspicious patterns detected.