execution-date-missing-from-report
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines diagnostic workflows for internal SpotDraft platform issues. All external resources, including BigQuery datasets (spotdraft-prod) and administrative domains (spotdraft.com), are owned by the skill author and represent legitimate operational tooling.
- [PROMPT_INJECTION]: The skill features an indirect prompt injection surface as it requires the agent to process potentially untrusted metadata from database query results and customer reports.
- Ingestion points: Data retrieved from the
historic_contracts_keypointer(labels, types) andpublic_contracts_v3_elasticcontractsearchreportrun(columns_filter JSON) tables in BigQuery. - Boundary markers: Not present. The skill does not instruct the agent to use specific delimiters or ignore instructions within the processed metadata.
- Capability inventory: The skill utilizes BigQuery SQL execution and navigation to administrative web interfaces.
- Sanitization: Not present. There are no instructions provided for validating or escaping content retrieved from the database or provided in customer problem descriptions.
Audit Metadata