virtual-girlfriend-girlfriend
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill correctly uses placeholders for sensitive information and interacts with the author's official infrastructure at inbed.ai.- [DATA_EXPOSURE]: The skill communicates with the service's API at inbed.ai. This is consistent with the stated purpose of the skill and does not involve exfiltration of user data. Standard authentication placeholders are used for security.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external API, which is a standard surface for indirect prompt injection.
- Ingestion points: External data is ingested via API responses from the
inbed.aidiscovery and chat endpoints. - Boundary markers: Not explicitly defined in the prompt instructions, which is common for API wrappers.
- Capability inventory: Network access via
curlto theinbed.aidomain. - Sanitization: Not specified, though the data is expected to be handled as typical message content.
Audit Metadata