telemetry-ops
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external network telemetry data, which represents an attack surface for instructions embedded in logs or event messages.
- Ingestion points: Data received from external network devices via syslog, SNMP traps, IPFIX, and gNMI streaming telemetry.
- Boundary markers: The documentation does not specify the use of delimiters or isolation markers for the ingested telemetry content.
- Capability inventory: The skill coordinates multiple MCP servers (syslog-mcp, snmptrap-mcp, ipfix-mcp, gnmi-mcp) to aggregate and query network events.
- Sanitization: There is no mention of specific sanitization or filtering logic applied to the incoming telemetry payloads before they are processed by the agent.
Audit Metadata