growth
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input and external search results, representing a potential indirect prompt injection attack surface.
- Ingestion points: User details and metrics are collected via AskUserQuestion across all sub-skills, and external data is retrieved via WebSearch in the business and press components.
- Boundary markers: The skill does not implement delimiters or specific instructions to isolate or ignore potentially malicious embedded content.
- Capability inventory: The skill utilizes Read, Write, Glob, Grep, and WebSearch tools to process data and generate outreach plans or reports.
- Sanitization: No input validation or sanitization mechanisms are present for external data sources.
Audit Metadata