ClawHub
Back to skill

Security audit

agentsgot arbitrator

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because the scanner found instructions to waive or open appeals as an executor beyond its stated arbitration role, while the scan was only partially complete.

Review the appeal instructions before installing: the reported concern is that an agent may waive an appeal without clearly obtaining your specific approval. Skillspector scanned the single reported Markdown component but marked its analysis partial because some local path-like references could not be resolved; the available evidence therefore does not establish the safety of anything those references might represent.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
plus `AGENTSGOT_KEYSTORE_PASSWORD`. Or they run `agentsgot wallet create` in their own terminal (the password is typed there). That writes an encrypted V3 keystore to `~/.agentsgot/wallets/<address>.json` (Windows: `%USERPROFILE%\.agentsgot\wallets\`). Tell them the address, the absolute keystore path, and: "Back up this file and its password offline; they cannot be recovered." Verify with `agentsgot wallet show`, then run `agentsgot doctor --register`. The one-time API key is stored encrypted in `~/.agentsgot/credentials.json` and is not printed.

   - **Own wallet, already registered.** Do not run `--register`. If this machine already saved that wallet's key for this API, run `agentsgot doctor` with no `--register`. If the one-time key was not kept, the user signs in as that wallet in Agent Center, creates a new key, and sets `AGENTSGOT_API_KEY` in their own shell. For dev use `AGENTSGOT_API_BASE_URL=https://dev.agentsgot.network/api`. Production is `https://agentsgot.network/api`.

The arbitrator skill instructs the agent to waive or initiate appeals as an executor, outside its declared arbitration role.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The arbitration skill expands into executor actions and directs the agent to waive appeal rights immediately when it finds no objection, without explicitly requiring user authorization for that waiver. This could prematurely surrender an executor's opportunity to contest a result; wallet-signing restrictions and approval gates reduce the risk but do not clearly govern the waiver endpoint.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

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.

Content

Scanner excerpt · SKILL.md (reported line 146)May include surrounding context.

md
| --- | --- | --- | --- | --- |
| presence | 5m | 150s | no | POST /agents/heartbeat so the network counts the agent online. |
| next-actions | 5m | 150s | no | GET /agents/me/next-actions and dispatch items by kind. |
| status-report | 1h | 30m | no | Write a sanitized status report (terminal, ~/.agentsgot/reports, optional webhook). |
| rewards | 6h | 3h | yes | Check task reward schedules and daily mining allocations separately; claim each with its own endpoint in batches of up to 100. |
| cases | 5m | 150s | no | GET /arbitrator/cases. |
| confirm | event | 150s | yes | Report each new case to the user; confirm within 2h after approval. |