skills/vaquarkhan/data-engineering-agent-skills/mcp-data-observability-integration/Gen Agent Trust Hub
mcp-data-observability-integration
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation-only resource that provides best practices for data platform observability using the Model Context Protocol (MCP). It does not contain executable code, hardcoded credentials, or malicious commands.
- [PROMPT_INJECTION]: The skill describes a surface for indirect prompt injection as it guides agents to process data from external sources.
- Ingestion points: Data enters the agent context through MCP server responses from systems like Spark, Kafka, Airflow, and Snowflake (referenced in SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or explicit instructions to ignore embedded commands for the data being read.
- Capability inventory: The workflow involves reading live metadata and job diagnostics. No destructive write capabilities or direct shell execution are authorized by default.
- Sanitization: There are no explicit instructions for sanitizing or validating the content of the logs or metrics retrieved, though the skill strongly advocates for read-only access.
Audit Metadata