signals-scout-customer-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from event properties and account metadata, which are external data sources that could be used to inject malicious instructions.
- Ingestion points: The skill ingests untrusted data via the
execute-sqltool from theevents,system.accounts, andsystem.account_relationshipstables (SKILL.md). - Boundary markers: The instructions lack defined delimiters or boundary markers to isolate untrusted data from the agent's logic.
- Capability inventory: The skill possesses reporting and storage capabilities including
emit_report,edit_report,execute-sql, andscout-scratchpad-remember(SKILL.md). - Sanitization: No explicit data sanitization, validation, or escaping procedures are specified for the data retrieved from database fields.
Audit Metadata