product-trend-researcher
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to ingest and analyze data from untrusted external sources, creating an attack surface for indirect prompt injection. Ingestion points: The agent is instructed to use social media trends, search analytics, and third-party research tools (e.g., Google Trends, SEMrush, Ahrefs) as data sources. Boundary markers: The instructions do not define specific delimiters to isolate potentially malicious content embedded in the researched data. Capability inventory: The skill is configured to perform automated monitoring, pattern recognition, and provide strategic recommendations based on the gathered data. Sanitization: No data sanitization or filtering logic is described for input from external research sources.
Audit Metadata