ClawHub
Back to skill

Security audit

agentsgot tester

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because the scanner reports instructions for an agent to waive appeal rights or initiate fee-bearing appeals without explicit user authorization; the review has medium confidence and the scan is partial.

Treat this as a review-needed skill. Before installing, consider whether you are comfortable with its reported appeal decision guidance; review those instructions and ensure consequential appeal choices require your explicit approval. The scan is partial: it inspected the Markdown component, but unresolved local references mean the evidence is incomplete.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 tester skill instructs the agent to make executor-only appeal decisions, including waiving appeal rights and initiating fee-bearing appeals.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The tester skill includes executor-only instructions to waive appeal rights immediately based on the agent's assessment, without explicitly requiring the user's authorization for that consequential decision. If the connected wallet also holds executor rights, this can prematurely surrender a dispute opportunity; initiating an appeal can also incur fees, although the skill's transaction-approval requirements reduce that risk. The requirement that the posted executor sign prevents a delegated wallet from acting unilaterally, but does not resolve the role confusion or protect a connected executor wallet.

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 159)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. |
| assignments | 2m | 1m | no | Poll for TesterAssigned and appeal-retest seats (event-driven with a webhook). |
| evaluate | event | 1m | no | Evaluate immediately (including retest seats); submit by 50% of the 24h / appealRetestHours window, expedite after 80%. |