exist
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes actions using the vendor-owned
@useclawlink/clitool vianpx. These commands are used for authenticating with the service and interacting with the Exist API. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from the external Exist API. While this creates a surface for potential injection if a user's health data contained malicious prompts, it is an inherent property of data-retrieval skills and is mitigated by the agent's internal safety guardrails.
- Ingestion points: Data is ingested via
npx @useclawlink/cli run existwhich returns data from the Exist service. - Boundary markers: Not explicitly defined in the skill instructions.
- Capability inventory: The skill has the capability to execute shell commands and read/write to the Exist API.
- Sanitization: Standard CLI output handling; no specific sanitization is defined in the instructions.
Audit Metadata