financial-graph-architect
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and executes the 'graphifyy' package from a public registry using the 'uv' tool runner to process financial data.
- [COMMAND_EXECUTION]: The skill executes shell commands to initialize project indexing and to serve data via the Model Context Protocol (MCP).
- [INDIRECT_PROMPT_INJECTION]: The skill indexes financial records which may contain untrusted data. Evidence: 1. Ingestion points: Local project files (ledgers, financial statements) processed by the indexing tool in SKILL.md. 2. Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are present for the ingested data. 3. Capability inventory: The skill has the ability to execute shell commands via 'uv' and write output files like 'graph.json' and 'graph.html'. 4. Sanitization: No sanitization or validation of external financial content before processing is documented.
Audit Metadata