designing-referral-programs
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, design frameworks, and email templates. It does not contain any functional code, shell commands, or instructions to perform network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill specifies the ingestion of marketing context from a local project file and user-provided business metrics.
- Ingestion points: The agent is instructed to read .claude/product-marketing-context.md and gather customer LTV and CAC data.
- Boundary markers: No explicit boundary markers or ignore instructions for the external data are present.
- Capability inventory: The skill does not define or utilize any capabilities for network access, file writing, or system command execution.
- Sanitization: No content sanitization is performed as the skill only provides documentation.
Audit Metadata