knowledge-graph
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external data, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: The skill description explicitly identifies 'documents, notes, web content, transcripts, research materials, or code repositories' as input sources.\n
- Boundary markers: The instructions do not include requirements for boundary markers or specific guidance for the agent to ignore instructions found within the processed source data.\n
- Capability inventory: The skill has the capability to write multiple files to the local filesystem (the
entities/directory andrelations.jsonl).\n - Sanitization: There are no explicit instructions to sanitize or escape content extracted from external sources before it is written to the output files.\n- [COMMAND_EXECUTION]: The skill description mentions the use of the 'ov compile' command to create or refresh graph artifacts, indicating that the agent is expected to execute local CLI tools.
Audit Metadata