dt-obs-problems
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external telemetry data which could potentially contain malicious instructions from an attacker-controlled source.
- Ingestion points: The skill utilizes 'fetch dt.davis.problems' and 'fetch logs' to retrieve external data into the agent's context (SKILL.md, problem-correlation.md).
- Boundary markers: The provided DQL templates do not include explicit delimiters or instructions to ignore embedded content within the retrieved telemetry.
- Capability inventory: The skill is primarily used for data retrieval and analysis via the DQL toolset; no dangerous capabilities like subprocess execution or file system modification were identified.
- Sanitization: No explicit sanitization or validation of the ingested telemetry content is mentioned in the instructions.
- [NO_CODE]: The skill consists entirely of Markdown documentation and DQL templates, with no executable scripts or binaries included.
Audit Metadata