ClawHub
Back to skill

Security audit

Himalaya

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Himalaya email CLI reference, but users should avoid the plaintext password example in one configuration section.

Install only if you intend to let Codex help operate your Himalaya email account. Prefer `pass`, system keyring, or another secure command for passwords, and do not copy the plaintext `auth.raw` example into a shared, backed-up, or source-controlled config file.

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
  • 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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation includes example configuration that stores IMAP/SMTP passwords directly in `backend.auth.raw` and `message.send.backend.auth.raw`. Even though a later section says raw passwords are for testing only and not recommended, the insecure pattern appears in the primary 'Minimal IMAP + SMTP Setup' example, which users are likely to copy verbatim, risking credential exposure via plaintext config files, backups, shell access, or source control.

Static analysis

No suspicious patterns detected.