skills/clerk/skills/audit-expo-skill/Gen Agent Trust Hub

audit-expo-skill

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads source code and documentation from official vendor repositories on GitHub (github.com/clerk/javascript and github.com/clerk/clerk-docs). These operations are used to establish a source of truth for the audit process and are directed at the author's own infrastructure.
  • [COMMAND_EXECUTION]: Shell commands including mkdir, cd, and git clone are used to manage local workspace directories and fetch required source data. These commands are localized to the project environment and are standard for repository maintenance tasks.
  • [DATA_EXFILTRATION]: Network access is limited to fetching data from the official developer repositories. The skill does not access sensitive system files (e.g., SSH keys, AWS credentials) or transmit local data to unauthorized third-party endpoints.
  • [PROMPT_INJECTION]: The skill instructions do not contain attempts to bypass AI safety guidelines or override system prompts. It uses structured developer instructions to perform technical comparisons and file updates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 04:53 PM
Security Audit — agent-trust-hub — audit-expo-skill