signals-scout-customer-analytics-billing-and-usage
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as account notebooks, Slack channel summaries, and synchronized communications which could contain untrusted content.
- Ingestion points: Data is retrieved through tools like
accounts-notebooks-list,accounts-summaries-list, and SQL queries against external data sources. - Boundary markers: The prompt includes explicit defensive instructions to treat these sources as untrusted data and to ignore any embedded directives or tool requests.
- Capability inventory: The skill possesses the ability to execute SQL queries and generate or edit reports through the report channel tools.
- Sanitization: The instructions mandate that the agent independently verify any claims found in external data against objective billing and usage timelines before taking action.
Audit Metadata