ln-75-architecture-diagram-builder
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository data such as source code, infrastructure-as-code scripts, and configuration files to generate diagrams. This creates a surface for indirect prompt injection where malicious instructions embedded in these files could attempt to influence the agent's behavior during processing.
- Ingestion points: Analyzes repository files, runtime wiring, IaC, contracts, and other project artifacts.
- Boundary markers: The instructions lack explicit delimiters or directions to the agent to ignore potentially malicious instructions embedded within the source data.
- Capability inventory: The skill includes the ability to read various repository files and write or patch diagram artifacts in documentation directories.
- Sanitization: There is no mention of sanitizing or validating input data before it is interpolated into the diagram source code.
Audit Metadata