find-projects-and-products
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external URLs, which creates a potential surface for indirect prompt injection where instructions could be embedded in the processed content.
- Ingestion points: The agent is directed to read content from
https://life.ayushrai.site/sites/projects/andhttps://life.ayushrai.site/sites/products/inSKILL.md. - Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard formatting or commands contained within the fetched data.
- Capability inventory: The skill provides instructions for using API endpoints at
https://life.ayushrai.site/askand a sandbox environment athttps://life.ayushrai.site/api/v1/sandbox. - Sanitization: There are no specified sanitization or validation steps for the content retrieved from the external sites before it is processed by the agent.
Audit Metadata