metals-agent-teneo
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill setup requires installing the
@teneo-protocol/sdkpackage from npm. This package and its associated GitHub organization (TeneoProtocolAI) are not part of the trusted external sources list, making it an unverifiable dependency. - [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection because it ingests and displays data from an external WebSocket.
- Ingestion points: Data retrieved via
sdk.sendMessageinSKILL.md. - Boundary markers: None provided in the usage examples.
- Capability inventory: Performs network read operations via WebSockets.
- Sanitization: No sanitization or validation of the remote content is shown before it is passed to the agent context.
- [DATA_EXFILTRATION] (SAFE): No evidence of sensitive local file access or unauthorized data transmission. Network communication is limited to the documented WebSocket endpoint.
Audit Metadata