palace-diagram
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and visualizes data from a knowledge graph database, which creates a potential surface for indirect prompt injection if the ingested data contains malicious instructions designed to influence the agent's behavior.
- Ingestion points: Untrusted data enters the context through the
knowledge_graph.dbfile referenced in theSKILL.mdusage examples. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content embedded within the database text.
- Capability inventory: The skill utilizes the
PalaceRendererPython class for logic and theMermaid ChartMCP tool for external rendering. - Sanitization: The skill documentation does not describe any sanitization, validation, or escaping of the data retrieved from the database before it is incorporated into diagrams.
Audit Metadata