onboarding

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data access were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential ingestion surface for untrusted data.
  • Ingestion points: The instructions in SKILL.md prompt the agent to read .agents/marketing-context.md if it exists in the project context.
  • Boundary markers: Absent; there are no specific instructions or delimiters provided to ignore potentially malicious directives within the context file.
  • Capability inventory: The skill is restricted to generating text-based design and optimization deliverables (journey maps, event contracts). It lacks access to any tools for code execution, file system modification, or network operations.
  • Sanitization: Absent; the external marketing context is processed directly to inform the onboarding design analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:55 AM
Security Audit — agent-trust-hub — onboarding