marketing-psychology
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted external data sources, creating a standard surface for indirect prompt injection.
- Ingestion points: The instructions direct the agent to process project templates, pricing configurations, analytics exports, session recordings, support tickets, and on-page survey answers (found in
SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill includes an embedded Python script for sample size calculations and instructions for file-reading and data synthesis.
- Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external files or user feedback channels.
Audit Metadata