axiom-apl
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate documentation and reference material for the Axiom observability platform.
- [COMMAND_EXECUTION]: The Bash tool is configured with a restricted set of Axiom CLI commands (query, dataset list, stream, config get). This ensures the agent is limited to operations necessary for data analysis and cannot perform administrative or destructive actions.
- [PROMPT_INJECTION]: Surface for indirect prompt injection detected. Ingestion points: external data from 'axiom query' output. Capability inventory: Bash tool for Axiom CLI operations. Boundary markers and sanitization are not implemented in the documentation-focused context. This is documented as a functional risk factor of data processing.
Audit Metadata