searching-mlflow-docs

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill performs network requests to mlflow.org to retrieve documentation index and markdown files. While these are legitimate sources for the skill's purpose, they are not on the pre-approved whitelist.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill ingests external content from the web (Step 1 index and Step 2 documentation) and feeds it into the agent's context.
  • Ingestion points: https://mlflow.org/docs/latest/llms.txt and [path].md files.
  • Boundary markers: None. The prompts do not instruct the agent to ignore instructions found within the fetched content.
  • Capability inventory: Limited to WebFetch and presenting results. No file-write, command-execution, or credential-access capabilities were identified.
  • Sanitization: No sanitization or validation of the remote content is performed before presentation.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:13 AM