referral-program

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely informational and focuses on marketing strategy. It contains no executable scripts, shell commands, or network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read context from .agents/product-marketing-context.md. While this is a data ingestion point, the skill lacks any capabilities (such as file-writing, network access, or command execution) that could be exploited via malicious content in that file.
  • [EXTERNAL_DOWNLOADS]: The skill mentions various well-known third-party services and tools (e.g., Stripe, Rewardful, Tolt) for referral program implementation, but does not perform any automated downloads or executions from these sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 03:36 PM