moat-analyzer
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its use of web search tools to gather business intelligence. Malicious content hosted on searched websites could attempt to influence the agent's scoring, calculation of risk, or the generation of startup opportunities.
- Ingestion points: Data from external websites enters the agent's context via the
web_searchtool output during the Research phase (documented inSKILL.md). - Boundary markers: The instructions do not include specific delimiters or 'ignore' instructions to separate untrusted web content from the agent's core instructions.
- Capability inventory: The skill's capabilities are limited to web searching and text generation; it lacks permissions for file system modification, command execution, or network requests to arbitrary endpoints.
- Sanitization: There is no evidence of filtering or validation of the data retrieved from the web before it is used to calculate moat scores and risk tiers.
Audit Metadata