referral-program

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected in the analyzed files.
  • [PROMPT_INJECTION]: The skill uses instructional language to set a marketing persona but does not attempt to bypass safety guidelines or override system prompts.
  • [DATA_EXPOSURE]: The skill mentions reading a product marketing context file (.claude/product-marketing-context.md) to improve its recommendations, which is a standard benign practice for providing contextual AI assistance.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 03:47 PM