codependix-export
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and metadata do not contain any detected malicious patterns, such as prompt injection, hardcoded credentials, or unauthorized command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a tool that processes untrusted project data (source code, dependencies, and configuration) to generate Markdown-based Mermaid diagrams and JSON reports. This represents a vulnerability surface where malicious content in source code could potentially be rendered into documentation.
- Ingestion points: Local project files,
tsconfig.json, and Nx project graphs mentioned inSKILL.md. - Boundary markers: Output diagrams are explicitly wrapped in
<!-- codependix:start ... -->and<!-- codependix:end ... -->markers to delimit generated content. - Capability inventory: The tool reads file system structures and project dependencies to produce visualizations.
- Sanitization: The documentation notes that node identifiers are sanitized and specific character sequences like
-->are escaped as-->to prevent breaking HTML comment structures in Markdown.
Audit Metadata