genpark-marketing-email-spamprevent-skill

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches skill source code from the vendor's GitHub repository (alphaparkinc) and installs standard Python dependencies including requests and python-dotenv from the official package registry.
  • [DATA_EXFILTRATION]: Transmits email subject lines and body text to the vendor's API endpoint (api.genpark.ai) for the purpose of spam score calculation and deliverability analysis as described in the skill's core functionality.
  • [PROMPT_INJECTION]: The skill processes untrusted email content provided by users, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Email subject and body content are ingested via analyze_copy, batch_analyze, and test_newsletter_template functions as seen in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided usage examples.
  • Capability inventory: The skill scripts have capabilities for network access (via the requests library to communicate with the vendor API) and local file reading (via the open() function in template testing).
  • Sanitization: No specific sanitization, filtering, or validation logic for the ingested email content is documented in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:05 AM
Security Audit — agent-trust-hub — genpark-marketing-email-spamprevent-skill