email-sequence

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is composed entirely of markdown instructions and reference templates designed to guide the AI in generating email copy.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it instructs the agent to ingest data from external files.\n
  • Ingestion points: Reads marketing context from .agents/product-marketing-context.md and .claude/product-marketing-context.md (SKILL.md).\n
  • Boundary markers: Absent; the skill does not specify delimiters or provide instructions to ignore embedded commands within the ingested content.\n
  • Capability inventory: This skill does not possess direct shell execution, file-writing, or network exfiltration capabilities, though it provides guidance on using external email tools.\n
  • Sanitization: Absent; the agent is not instructed to validate or sanitize the content of the marketing context files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 12:10 PM
Security Audit — agent-trust-hub — email-sequence