ad-creative
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection through its ingestion of external data.
- Ingestion points: The skill reads marketing details from 'marketing-context.md' and processes user-supplied ad copy for iteration.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious embedded commands within these external files.
- Capability inventory: The skill has access to execute a local Python script for copy validation.
- Sanitization: No explicit validation or escaping of ingested text is performed before it is added to the model context.
- [COMMAND_EXECUTION]: The skill includes and executes a local Python utility ('scripts/ad_copy_validator.py') to ensure ad copy meets platform character limits and compliance rules. This script uses only standard library components and performs local text analysis, which is an appropriate and safe use of technical capabilities for the skill's purpose.
Audit Metadata