account-intelligence-analyst
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized execution were detected. The skill's behavior matches its stated purpose of providing account-based intelligence.
- [DATA_EXPOSURE]: The skill is designed to access and analyze sensitive business data from CRM systems (HubSpot) and external enrichment tools (Clay). It also processes uploaded files containing contact information and account research. This access is limited to the tools and files provided by the user for the intended purpose of generating sales briefings.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including web search results and uploaded reports (PDF/CSV/JSON) from third-party services like Humantic AI and Apollo.
- Ingestion points: Processes uploaded reports and web fetch/search results in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters to separate untrusted data from the system prompt.
- Capability inventory: The skill can perform CRM searches, trigger company enrichment tools, and write to the local file system (saving markdown briefings).
- Sanitization: No specific sanitization or filtering of external content was observed in the instructions.
Audit Metadata