18-referral-program
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and does not contain any executable scripts, shell commands, or network operations.
- [NO_CODE]: No code (Python, Node.js, etc.) is included in the skill.
- [INDIRECT_PROMPT_INJECTION]: While the skill instructs the agent to read context from
.agents/product-marketing-context.md, it does not perform any high-risk actions such as writing to the file system or executing arbitrary commands based on that data, effectively neutralizing the risk of indirect prompt injection.
Audit Metadata