skills/reason-machines/marketing-skills/genpark-marketing-cloud-sql-audience-generator/Gen Agent Trust Hub
genpark-marketing-cloud-sql-audience-generator
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes natural language user input to generate SQL queries that are subsequently executed in a Salesforce Marketing Cloud environment. This creates a surface for indirect prompt injection where malicious instructions could influence the generated SQL. Ingestion points: Natural language intent processed in SKILL.md. Boundary markers: Absent; no specific delimiters or ignore-instructions are used for the user input. Capability inventory: The skill includes the ability to execute generated SQL via MarketingCloudClient.execute_query as shown in SKILL.md. Sanitization: Absent; there is no evidence of input filtering or sanitization before the generation process.
- [EXTERNAL_DOWNLOADS]: The installation process involves cloning a remote repository and installing dependencies from an external source. Evidence: git clone https://github.com/alphaparkinc/genpark-marketing-cloud-sql-audience-generator-skill.git and pip install -r requirements.txt in SKILL.md.
Audit Metadata