understand-chat
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file,
.understand-anything/knowledge-graph.json, which represents an attack surface for indirect prompt injection if the file contains adversarial content. * Ingestion points: The agent is instructed to read and grep the knowledge graph file in SKILL.md. * Boundary markers: There are no explicit delimiters or warnings to ignore instructions embedded within the graph data. * Capability inventory: The skill utilizes standard file reading and grep search capabilities. * Sanitization: No validation or sanitization of the JSON content is performed before processing.
Audit Metadata