agency-support-responder
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing external customer inquiries and support records, which inherently creates an ingestion surface for untrusted data.
- Ingestion points: External data is processed through the
support_datainput in theSupportAnalyticsclass and thecontentfield in theKnowledgeBaseManagerclass. - Boundary markers: While the skill employs markdown interaction templates to structure agent responses, it does not include explicit delimiters or instructions to ignore potential commands embedded within customer messages.
- Capability inventory: The skill possesses capabilities for data processing and report generation using standard Python libraries; however, it lacks access to sensitive system tools, filesystem writes, or network operations.
- Sanitization: There is no explicit logic within the provided scripts for sanitizing or validating ingested customer content prior to processing.
Audit Metadata