digital-marketing-pro-claude-plugin

Warn

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is distributed through a third-party marketplace and a personal GitHub repository (indranilbanerjee/digital-marketing-pro) that are not verified trusted sources.\n- [COMMAND_EXECUTION]: The plugin includes 70 execution scripts used for tasks like analytics and research. Executing code from an unverified source represents a potential security risk.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from target URLs during SEO audits and external files (PDF/DOCX) during brand profiling. This data is used to generate marketing content and strategies, which could be leveraged for indirect prompt injection.\n
  • Ingestion points: Target URLs in /seo-audit and document imports in /import-guidelines.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are documented for processing ingested data.\n
  • Capability inventory: Writing files to the local home directory (~/.claude-marketing/) and making network requests via various integrated marketing APIs.\n
  • Sanitization: The documentation does not describe any sanitization or validation of external data before processing.\n- [DATA_EXFILTRATION]: The skill requests and manages API keys for numerous marketing platforms (Google Ads, HubSpot, etc.). While functional, the central collection of these credentials and access to local brand data creates a significant data exposure risk.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 18, 2026, 05:05 PM
Security Audit — agent-trust-hub — digital-marketing-pro-claude-plugin