dt-obs-services
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Dynatrace platform (such as service names, endpoint identifiers, and span attributes) which could potentially be manipulated to include malicious instructions targeting the agent.
- Ingestion points: Data enters the agent's context through tools like
create-dqlandstatic-threshold-analyzerwhich fetch performance metrics and trace data. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore instructions embedded within the processed data.
- Capability inventory: The skill utilizes
create-dql,static-threshold-analyzer,get-entity-name, andask-dynatrace-docsto perform its primary function. - Sanitization: There are no defined sanitization or validation steps for the data retrieved from DQL queries before it is analyzed or presented to the user.
Audit Metadata