logfire-query
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill handles telemetry data (logs, spans, traces) that may originate from untrusted external sources, presenting a theoretical surface for indirect prompt injection. This is inherent to the primary function of a log analysis tool.
- Ingestion points: Data is ingested via the
query_runtool and REST API endpoints (SKILL.md). - Boundary markers: The instructions do not define specific delimiters for separating data from instructions, though they emphasize classification and routing.
- Capability inventory: The skill utilizes SQL querying (query_run) and platform link generation (project_logfire_link).
- Sanitization: Documentation explicitly advises using parameterized queries (pyformat style) in programmatic environments to prevent injection (references/client-usage.md).
- [EXTERNAL_DOWNLOADS]: The skill correctly references official and well-known vendor resources for Pydantic/Logfire, including API domains (logfire-api.pydantic.dev) and standard libraries (logfire, pyarrow). These are documented neutrally as required for trusted vendor functionality.
Audit Metadata