referral-program

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): The skill uses standard role-play instructions ('You are an expert...') without any attempts to bypass safety filters or override system-level constraints.\n- [Data Exposure & Exfiltration] (SAFE): There are no commands for accessing sensitive system files or credentials. All content is static marketing advice.\n- [Remote Code Execution] (SAFE): No remote scripts, package installations, or dynamic code execution patterns are present.\n- [No Code] (SAFE): The skill contains no executable code files (.py, .js, .sh), only documentation and templates.\n- [Indirect Prompt Injection] (INFO): The skill references a local context file (.claude/product-marketing-context.md). While this is an ingestion surface for external data, the skill possesses no capabilities (write operations, command execution) to exploit such an injection.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 04:30 AM