ClawHub
Back to skill

Security audit

Corrie site check

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly described, read-only website checks and Corrie monitoring lookups with proportionate access.

Corrie receives the URL you check, so avoid URLs containing secrets or sensitive query parameters. Keep the account API token in an environment variable and out of chat logs. The header and certificate check is not a full security audit.

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 (2)

The site-check workflow sends the user's supplied URL to Corrie without an explicit privacy disclosure.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The skill instructs the agent to submit the selected URL to Corrie's external service through MCP or HTTP, but does not warn the user that their supplied URL will be shared with that third party. Restricting checks to public sites does not eliminate disclosure of which URL the user requested to check.

Content

No source excerpt is available for this finding.

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 22)May include surrounding context.

If it is not connected, call the same public endpoint over HTTP. It needs no key:

bash
curl -s https://corrie.io/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_website","arguments":{"url":"example.com"}}}'