ad-copy-generation
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute local Python scripts, specifically
scripts/generate-rsa.pyandscripts/analyze-ad-performance.py. These scripts are used to perform the core functions of the skill, such as generating ad variations and analyzing performance metrics. This is standard behavior for a tool-based marketing skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external landing page URLs and local CSV files. While this represents a surface for indirect prompt injection where malicious instructions could be embedded in the webpage or performance data, the skill's capabilities are limited to generating ad copy and do not include high-privilege operations.
- Ingestion points: Content fetched from user-provided landing page URLs and data read from local performance.csv files.
- Boundary markers: None explicitly defined in the provided markdown file.
- Capability inventory: Execution of local Python scripts for data processing and copy generation.
- Sanitization: The skill includes instructions to validate character limits and verify Google Ads policy compliance.
Audit Metadata