understand-chat
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes the contents of
.understand-anything/knowledge-graph.json, which is a data source that could potentially contain untrusted information if the graph was generated from a codebase containing malicious comments or metadata. - Ingestion points: Reads from
.understand-anything/knowledge-graph.json(SKILL.md, Instructions 1-6). - Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the prompt templates.
- Capability inventory: The agent is authorized to read local files and use search tools (grep) to explore the project structure.
- Sanitization: The skill does not implement sanitization or validation of the graph content before it is processed by the agent.
Audit Metadata