datadog-apm
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes trace and service data from Datadog, which could include metadata or error messages controlled by external sources.
- Ingestion points: Trace data and service summaries retrieved through the Datadog API (SKILL.md).
- Boundary markers: None explicitly defined to separate tool outputs from agent instructions.
- Capability inventory: The skill is limited to read-only diagnostic tools; no tools for command execution, file system writes, or unauthorized network operations are present.
- Sanitization: No specific sanitization of external data is defined in the instructions.
Audit Metadata