ClawHub
Back to skill

Security audit

trenchytools

Security checks for vulnerabilities and agentic risk

Overview

The skill’s trading access, local wallet signing, and token uploads fit its stated purpose, with no concrete evidence of malicious behavior.

Use a dedicated wallet with limited funds, verify transaction amounts and fees before signing, and protect wallet backups. Treat uploaded token images and metadata as public and potentially persistent. Review the live remote instructions before granting trading authority.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
(Robinhood Chain) and submit. Keys never leave the machine.

- Base URL: `https://api.trenchy.tools`
- Agent instructions: `https://api.trenchy.tools/AGENTS.md` (read this first)
- Spec: `https://trenchy.tools/openapi.json` · Live capabilities: `GET /api/chains`
- Only use paths that exist in the spec; never invent endpoints or fields.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

a key in the URL ends up in server logs, referrers and shell history.

bash
curl -H "x-api-key: ***" "https://api.trenchy.tools/api/me"

The query form (?api-key=***) still works and is the only option for the WebSocket

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

Get a key

bash
curl "https://api.trenchy.tools/api/create-api-key?label=my-agent"
# -> {"apiKey":"***"}  shown once; store it, then send it as the x-api-key header

The launch workflow uploads images and metadata to a third-party IPFS service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The launch workflow instructs the agent to send an image and token metadata to the TrenchyTools IPFS endpoint. It does not warn that this content leaves the user's machine and may become publicly retrievable and difficult to retract once published through IPFS.

Content

No source excerpt is available for this finding.