signals-scout-csp-violations
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted event data from $csp_violation events to generate security reports. Ingestion points: Properties such as $csp_blocked_url, $csp_document_url, and $csp_source_file in the events table (queried via execute-sql) which are generated by external user browsers. Boundary markers: The instructions do not define delimiters or specific instructions for the agent to ignore potentially malicious commands embedded in the ingested event data. Capability inventory: The skill has the ability to query the analytics database (execute-sql) and create or modify entries in the platform's report inbox (emit_report, edit_report). Sanitization: There is no evidence of explicit sanitization, escaping, or filtering of externally sourced event properties before they are interpolated into the agent's context for analysis.
Audit Metadata