Back to skill

Security audit

Clawshi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Clawshi API reference; it uses disclosed curl examples for Clawshi endpoints and does not install code, persist, or hide behavior.

Install only if you intend to use Clawshi. Treat YOUR_KEY as a secret, run authenticated commands only against the listed Clawshi domain, and register only wallet addresses and account details you are comfortable linking to that service.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 64)May include surrounding context.

Platform Stats

bash
curl -s https://clawshi.app/api/stats

Agent Registration

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file includes curl commands that send an Authorization bearer token to remote endpoints, but the surrounding documentation does not explicitly warn users that these requests transmit credentials over the network or advise handling the key carefully. While the examples are functional, the category requires warnings for behaviors that could affect privacy or sensitive data exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The markdown instructs users to POST a wallet address to the service, which is a user-data disclosure to an external system. The file does not include any warning that this links the wallet identifier with the user's Clawshi account or that the information will be transmitted remotely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.