analyzing-mlflow-trace
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes trace data containing untrusted application logs, inputs, and outputs.
- Ingestion points: Untrusted data enters the agent's context through the output of
mlflow traces getstored in/tmp/trace.json(SKILL.md). - Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings when processing span inputs or outputs from the trace file.
- Capability inventory: The skill uses
mlflowandjqfor file processing and metadata extraction; it does not utilize arbitrary code execution, file-write, or network operations. - Sanitization: No sanitization, escaping, or filtering of the trace content is mentioned before the data is processed by the agent.
Audit Metadata