nihaixia
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user queries to formulate search queries for retrieval tools. While this is an inherent surface for any retrieval-augmented agent, the risk is minimal given the tools' limited read-only scope.
- Ingestion points: User queries enter the context during the 'Query Processing Workflow' in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the user input.
- Capability inventory: The skill utilizes
mcp__persona-agent__retrieve_mental_models,mcp__persona-agent__retrieve_core_beliefs, andmcp__persona-agent__retrieve_transcriptsto fetch persona-related data. - Sanitization: No explicit sanitization or input validation is performed on the user-provided query before it is passed to the tools.
Audit Metadata