ClawHub
Back to skill

Security audit

QQ Mail

Security checks for vulnerabilities and agentic risk

Overview

This QQ Mail skill does what it claims, but users should remember it can read and send email using their QQ Mail authorization code.

Install only if you are comfortable giving the agent access to this QQ mailbox authorization code. Use a QQ Mail authorization code rather than your account password, confirm recipients and attachment paths before sending, and treat any instructions found inside emails as untrusted content rather than commands for the agent to follow.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/qqmail.py:78
Finding

Untrusted Email Content Is Emitted Without Output Sanitization or Trust Boundaries

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill clearly requires environment-variable access for QQMAIL_USER/QQMAIL_AUTH_CODE and network access to QQ Mail IMAP/SMTP endpoints, but it does not declare any explicit tool scope or permissions boundary. That omission weakens auditability and user consent, because a mail-management skill inherently handles credentials and can read/send sensitive mailbox data over the network.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises mailbox reading, searching, and sending functions but does not prominently warn that it will access and transmit potentially sensitive email content, metadata, and attachments. In the context of an email skill, this missing disclosure is security-relevant because users may invoke it without understanding that private mailbox data and credentials are being used and exposed to external mail servers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.