dt-obs-logs
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze application or infrastructure logs, which are external data sources.
- Ingestion points: Untrusted data enters the agent's context through the
contentfield when executingfetch logsqueries as described inSKILL.md. - Boundary markers: The skill does not instruct the agent to use delimiters or ignore instructions that might be embedded within the log content.
- Capability inventory: The skill enables log searching, pattern analysis, and JSON parsing using DQL tools.
- Sanitization: There is no evidence of sanitization, filtering, or escaping techniques applied to the
contentfield to prevent the agent from potentially following instructions found within log entries.
Audit Metadata