ai-dating
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curl.exein PowerShell to interact with the backend API, performing tasks like authentication, profile management, and file uploads. - [DATA_EXFILTRATION]: The skill transmits personal information, including email addresses, phone numbers, and social media handles, to the external service at
api.aidating.topto enable matchmaking functionality. - [EXTERNAL_DOWNLOADS]: The skill fetches data representing other users' profiles from an external API for processing.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from external user profiles.
- Ingestion points: Profile data retrieved from the
/match-tasks/{taskId}/checkendpoint as described inreferences/curl-api-operations.md. - Boundary markers: The instructions do not define boundary markers or provide warnings to the agent regarding embedded instructions in user-generated content.
- Capability inventory: The skill allows for network operations via
curl.exeand file system access for uploading images. - Sanitization: There is no mention of sanitizing or validating external content before it is processed by the model.
Audit Metadata