referral-program

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the instructions or reference files. The persona and workflows are consistent with the stated purpose of marketing growth engineering.
  • [DYNAMIC_EXECUTION]: The skill utilizes a local script (scripts/referral_roi_calculator.py) to perform ROI calculations. A technical audit of the script confirms it uses only standard Python libraries (json, sys) to process numerical data and produces text-based reports without performing network operations, shell execution, or file system modifications.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions to ingest data from a local marketing-context.md file. While this represents a data ingestion surface, it is a standard design pattern for providing business context and is not coupled with any dangerous tools or capabilities, making the risk profile negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 12:32 PM
Security Audit — agent-trust-hub — referral-program