email-sequence

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill files are composed of documentation and guidelines for email marketing. No scripts, binaries, or dangerous command executions were identified.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to load project-specific context from local files such as .agents/product-marketing-context.md. While this constitutes an ingestion of external data, it is a standard design pattern for context-aware agents to improve relevance and does not involve any dangerous capabilities or malicious instructions in this instance.
  • Ingestion points: SKILL.md (Initial Assessment section).
  • Boundary markers: Not explicitly defined in the prompt instructions.
  • Capability inventory: Primarily natural language generation for email copy and strategy advice.
  • Sanitization: Not present, as the context is intended to be used as a primary source of truth for the task.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 10:15 PM
Security Audit — agent-trust-hub — email-sequence