omh-codebase-uml
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to perform shell command execution using the
omhcommand-line utility and the Java/PlantUML runtime for codebase analysis and image rendering. Specific commands involve generating PlantUML source and executing rendering binaries to produce PNG files. - [INDIRECT_PROMPT_INJECTION]: The workflow involves ingesting and processing data from external repositories, which presents an attack surface for indirect prompt injection where malicious instructions embedded in the codebase could potentially affect agent operations or tool execution.
- Ingestion points: Local repository source files and directory structures processed by
omh codegraph uml(referenced in SKILL.md). - Boundary markers: No specific boundary markers or "ignore instructions" are implemented for the ingested codebase data.
- Capability inventory: Shell command execution via
omh,java, andplantumltools, including file writing capabilities for output artifacts. - Sanitization: The skill does not define validation or sanitization procedures for the input repository data or the resulting diagram source code.
Audit Metadata