audit-data-contamination
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data sources, which creates a surface for indirect prompt injection. * Ingestion points: The input contract requires external data including dataset_partitions, training_sources, and evaluation_records. * Boundary markers: The instructions do not define delimiters or specific instructions for the agent to ignore embedded commands within the ingested content. * Capability inventory: The skill does not define its own tools or scripts, but the agent uses platform capabilities to perform the audit. * Sanitization: No sanitization or validation steps are defined for the ingested records.
- [NO_CODE]: The skill consists entirely of documentation and metadata; it does not include any scripts, binary files, or external package dependencies.
Audit Metadata