referral-program
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill is purely informational, providing guidelines for program design and optimization.
- [INDIRECT_PROMPT_INJECTION]: The skill reads a local context file (.claude/product-marketing-context.md), but lacks dangerous capabilities like network access or command execution to be exploitable. 1. Ingestion points: SKILL.md. 2. Boundary markers: absent. 3. Capability inventory: none. 4. Sanitization: absent.
Audit Metadata