searching-mlflow-docs
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external documentation, creating an inherent surface for indirect prompt injection. * Ingestion points: Data is fetched via WebFetch from mlflow.org/docs/latest/llms.txt and related markdown files as seen in SKILL.md. * Boundary markers: The skill includes explicit instructions to treat fetched content as untrusted reference data and to ignore embedded instructions or tool requests. * Capability inventory: There are no tools or scripts with dangerous capabilities like command execution or file system writes within the skill package. * Sanitization: The agent is instructed to summarize relevant documentation and independently validate any code blocks before presentation.
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation indices and content from the official mlflow.org domain.
- [NO_CODE]: This skill contains no executable scripts or binary files, relying exclusively on tool calls and natural language instructions.
Audit Metadata