metrickit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements handlers for external data payloads provided by the operating system (MXMetricPayload and MXDiagnosticPayload).
- Ingestion points: Payloads are ingested via the didReceive subscriber methods in SKILL.md and references/metrickit-patterns.md.
- Boundary markers: The skill does not implement specific delimiters for the ingested JSON data.
- Capability inventory: The skill includes capabilities to write data to the local file system (FileManager) and upload data to a network endpoint (URLSession).
- Sanitization: Data is converted to JSON representation, but no further sanitization of the telemetry content is described before storage or transmission.
Audit Metadata