spicetify

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a helper CLI and skill payloads hosted on the author's GitHub repository (github:wyattowalsh/spicetify-agent-skill), suggesting installation and execution via package managers like uvx or npx.- [COMMAND_EXECUTION]: Local system operations are mediated through the spicetify-agent tool. The instructions strictly prohibit the execution of arbitrary shell commands or unsanitized user input, requiring a dry-run phase and explicit confirmation for any system mutations.- [PROMPT_INJECTION]: The skill is designed to process and analyze untrusted third-party data, including theme READMEs, extension code, and Marketplace metadata. This ingestion of external content represents a potential surface for indirect prompt injection, which the skill addresses with policies for auditing, staging, and hashing content prior to execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:15 PM
Security Audit — agent-trust-hub — spicetify