Digital Marketing
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that involve ingesting untrusted data from external sources, creating a surface for indirect prompt injection. \n
- Ingestion points:
SKILL.mdandshort-form-video.mdinstruct the agent to analyze signals from comments, replies, and search queries to inform content and marketing decisions. \n - Boundary markers: There are no instructions for the agent to use delimiters or to treat embedded commands in external text as data rather than instructions. \n
- Capability inventory: The skill is intended to guide content generation and campaign planning, utilizing the inputs gathered from these external sources. \n
- Sanitization: The instructions lack any explicit steps for sanitizing, validating, or filtering the external content before processing it into marketing assets.
Audit Metadata