arize-link
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation-based utility that provides instructions and templates for generating Arize UI deep links. It does not include any scripts, executable code, or package dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data (IDs and time ranges) and interpolates them into URL templates. However, the risk is negligible as the skill only generates markdown links for user consumption and has no automated tool invocation or execution capabilities.
- Ingestion points: IDs and parameters gathered from user input, exported trace data, or parsed URLs (SKILL.md).
- Boundary markers: Absent; the skill does not include specific delimiters or instructions to the agent to ignore embedded commands in the provided IDs.
- Capability inventory: The skill is restricted to generating text/markdown links; it has no access to subprocesses, file writing, or network operations.
- Sanitization: The instructions explicitly require base64-encoding for path IDs and URL-encoding for version parameters (SKILL.md), which serves as a basic form of data normalization.
Audit Metadata