advertorial-writer

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a bash preamble and interactive prompts to manage its execution environment and user preferences.
  • It locates the skill root directory by searching for VERSION files in designated paths such as ~/.claude/skills/dtc-copywriting-skills.
  • It executes local binaries including rmbc-update-check, rmbc-analytics, and rmbc-workspace to handle versioning, logging, and workspace setup.
  • It uses sed to programmatically update telemetry settings within ~/.rmbc-skills/config.yaml based on user feedback.
  • [DATA_EXFILTRATION]: The skill implements a usage tracking system to monitor activity and improve the tool suite.
  • It captures metadata such as the skill name (advertorial-writer) and the active product name.
  • The skill provides a transparent opt-in mechanism via AskUserQuestion, ensuring no data is logged without the user's explicit consent.
  • [EXTERNAL_DOWNLOADS]: The skill performs network-related operations for maintenance and educational purposes.
  • The rmbc-update-check script contacts remote sources to determine if a newer version of the framework is available.
  • It offers to launch a YouTube training video using the system's open command, directing users to a well-known and trusted video platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 01:36 PM
Security Audit — agent-trust-hub — advertorial-writer