dt-obs-frontends
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows for processing untrusted telemetry data from external sources (web and mobile user interactions).
- Ingestion points: The skill ingests data from
user.eventsanduser.sessionstables via DQL queries. - Boundary markers: The provided DQL templates do not implement specific delimiters or warnings to prevent the agent from being influenced by malicious instructions embedded in telemetry fields (e.g., custom properties, error messages).
- Capability inventory: The skill enables the agent to query, summarize, and join data across Dynatrace Grail tables. No sensitive system-level capabilities like file writing or outbound network requests are included.
- Sanitization: No data sanitization or escaping mechanisms are applied to the external content before it is processed by the DQL queries.
Audit Metadata