datadog-incidents
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches incident details from an external source (Datadog API), creating a surface for indirect prompt injection. \n
- Ingestion points: Tools such as get_incident and list_incidents retrieve potentially untrusted data from the Datadog environment. \n
- Boundary markers: There are no specific instructions or delimiters provided to the agent to help it distinguish between its core instructions and data found within incident summaries or comments. \n
- Capability inventory: The skill provides tools for both reading (get_incident) and modification (update_incident), creating a path for malicious instructions in data to potentially trigger actions. \n
- Sanitization: No data sanitization, validation, or filtering logic is specified for the content retrieved from external API calls.
Audit Metadata