automated-knowledge-graph

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface. The skill is designed to ingest and process untrusted data from chat logs and documents to populate a knowledge graph.
  • Ingestion points: Extracting entities and relationships from chat and documents (SKILL.md).
  • Boundary markers: Absent. No markers are defined to separate user data from instructions during the extraction phase.
  • Capability inventory: The skill utilizes data persistence (Mermaid, Neo4j) and context retrieval for complex queries. No scripts or shell commands are included in the provided file.
  • Sanitization: No validation or sanitization logic is described for the extracted data or the generated graph.
  • [NO_CODE]: The skill package consists entirely of instructional markdown content. No executable scripts, binaries, or configuration files are provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 05:56 PM
Security Audit — agent-trust-hub — automated-knowledge-graph