skills/steipete/clawdis/himalaya/Gen Agent Trust Hub

himalaya

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [External Downloads] (SAFE): The skill installs the himalaya CLI via Homebrew. This is a trusted package management system and the source repository is a well-known open-source project.
  • [Command Execution] (LOW): The skill operates by executing himalaya shell commands. It supports the execution of local shell commands for password retrieval (e.g., via pass), which is a standard feature of the underlying tool.
  • [Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection because it processes untrusted email data.
  • Ingestion points: External email data is ingested via himalaya message read and himalaya envelope list commands.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between email content and system instructions.
  • Capability inventory: The skill can delete emails, send messages via template send, and download attachments.
  • Sanitization: No content sanitization or filtering of email bodies is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:18 PM