consulting-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, creating a potential surface for indirect prompt injection.
- Ingestion points: Phase 2 of the workflow accepts 'Data Summary' and 'External Search Findings' as inputs to synthesize the final report.
- Boundary markers: The instructions lack specific boundary markers or delimiters (e.g., XML tags or explicit 'ignore instructions' wrappers) for the external data being interpolated into the report context.
- Capability inventory: The skill has the capability to delegate tasks to other skills, specifically invoking visualization/charting tools like
data-analysis(Step 2.3). - Sanitization: There are no instructions for sanitizing or filtering the external content for embedded commands or prompt injection patterns before synthesis.
Audit Metadata