investor-management-skill
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill's instructions are limited to parsing and organizing data for the user.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external tools such as CRMs and spreadsheets, which constitutes a potential vulnerability surface if those sources contain malicious instructions.
- Ingestion points: Data is pulled from "
CRM" and "cap table/spreadsheet" as specified inSKILL.md. - Boundary markers: The instructions lack specific delimiters or "ignore" warnings to distinguish external data from core instructions.
- Capability inventory: The skill's actions are restricted to data parsing, formatting, and template output within the chat context.
- Sanitization: No sanitization or validation of the ingested external content is defined.
Audit Metadata