newsletter-digest

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, command execution, or unauthorized data access found.
  • [PROMPT_INJECTION]: The skill processes untrusted email content, creating an indirect prompt injection surface. Ingestion points: mcp__claude_ai_Gmail__gmail_read_message and mcp__claude_ai_Gmail__gmail_read_thread in SKILL.md. Boundary markers: None present. Capability inventory: mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, and mcp__context7 tools are utilized for external technical data retrieval. Sanitization: No input sanitization or filtering is performed on retrieved email content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 12:55 AM
Security Audit — agent-trust-hub — newsletter-digest