marketing-mix-modeling-mmm-pipeline
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to clone a repository from a third-party, untrusted GitHub account:
https://github.com/francescaetnom-wq/Marketing-Mix-Modeling-End-to-End-Pipeline.git. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external CSV files which acts as a potential attack surface.
- Ingestion points: The skill ingests data using
pd.read_csv('data/dt_simulated_weekly.csv')andpd.read_csv('data/dt_transformed.csv'). - Boundary markers: No boundary markers or delimiters are used to separate data from instructions during processing.
- Capability inventory: The skill has the capability to write to the file system (
to_csv) and execute mathematical modeling and optimization logic. - Sanitization: No sanitization or validation of the CSV contents is performed before the data is used in transformations and modeling.
Audit Metadata