RateVC
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its integration with external web data sources.\n
- Ingestion points: Investor profile data, deal history, and activity signals are retrieved from third-party websites including LinkedIn, Crunchbase, and regional registries (e.g., IT桔子, 36氪).\n
- Boundary markers: There are no explicit instructions in SKILL.md for the agent to use delimiters or to treat fetched web content as untrusted data distinct from its core instructions.\n
- Capability inventory: The agent uses retrieved data to perform multi-dimensional scoring and generate reports; it does not have capabilities for system modification or sensitive file access.\n
- Sanitization: The instructions do not define any validation or filtering mechanisms for the data retrieved from external sources.\n- [EXTERNAL_DOWNLOADS]: The skill fetches data from well-known business research platforms and official government databases (e.g., SEC EDGAR, AMAC) for legitimate diligence purposes.\n- [COMMAND_EXECUTION]: The documentation includes a setup command ('npx skills add') used to install the tool into the agent's environment.
Audit Metadata