graphify-query
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands using the
graphifyCLI tool, includinggraphify query,graphify path,graphify explain, andgraphify update. These commands are used to generate and interact with a local knowledge graph of the codebase. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository to answer questions about architecture and relationships. This creates an attack surface where malicious content within the codebase could attempt to influence the agent's output.
- Ingestion points: Reads data from
graphify-out/graph.json,graphify-out/wiki/index.md, andgraphify-out/GRAPH_REPORT.md. - Boundary markers: None identified in the instructions.
- Capability inventory: Can execute shell commands via the
graphifyCLI. - Sanitization: No evidence of output sanitization or filtering of the graph data before it is presented to the agent.
Audit Metadata