startup-intake
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected.
- [DATA_EXFILTRATION]: The skill is designed to collect sensitive business information, such as equity splits, financial metrics (MRR/ARR), and team details, through a structured interview process. This behavior is consistent with the skill's primary purpose of startup onboarding. The collected data is stored locally in the
./launchpad/directory, and no network exfiltration or unauthorized access to system files was identified. - [PROMPT_INJECTION]: The skill defines a clear instructional framework for the AI agent to follow during the interview process. It does not contain any patterns intended to bypass safety filters or override system instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input during the interview phase to populate a markdown artifact. While this represents a data ingestion surface, the skill lacks dangerous capabilities such as remote code execution or network operations that could be exploited via injection.
Audit Metadata