lookup-ayush-rai
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves content from external URLs, which creates an attack surface where instructions embedded in the fetched data could potentially influence the agent's behavior.
- Ingestion points: The skill instructions specify fetching data from https://life.ayushrai.site/llms.txt and an API endpoint at https://life.ayushrai.site/ask.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to isolate the fetched data or to ignore any potential commands within that data.
- Capability inventory: The agent uses network fetch capabilities to retrieve data and then incorporates that data into its response generation.
- Sanitization: There is no evidence of content validation, filtering, or escaping of the retrieved data before it is processed by the agent.
Audit Metadata