code-understand
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests the installation of the
@colbymchenry/codegraphpackage from the npm registry for enhanced analysis. - [COMMAND_EXECUTION]: The skill invokes the
obsidian-wikicommand line tool and potentially thenpmpackage manager to perform its tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source files to generate its focus map, which creates a vulnerability surface for indirect instructions. Ingestion points: Files located within the project directory specified by the
--projectflag. Boundary markers: No delimiters or instructions to ignore embedded content are identified in the skill. Capability inventory: Execution of local shell commands and file system read access. Sanitization: No explicit validation or sanitization of codebase content is mentioned.
Audit Metadata