referral-program
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of informational content and strategic frameworks for referral marketing. No executable code, scripts, or shell commands are present in the provided file.
- [SAFE]: The skill mentions reading marketing context from local files such as .claude/product-marketing-context.md. This is a potential surface for indirect prompt injection. However, since the skill has no external capabilities like network access or command execution, there is no exploit path. Evidence chain: 1. Ingestion points: .claude/product-marketing-context.md (SKILL.md); 2. Boundary markers: absent; 3. Capability inventory: none; 4. Sanitization: absent.
Audit Metadata