rc-improve-codebase-architecture
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute OS-specific commands (xdg-open, open, or start) to display a generated HTML report in the user's default browser.
- [EXTERNAL_DOWNLOADS]: The generated architecture report references external CSS and JavaScript libraries from Tailwind and Mermaid CDNs. These are well-known technology services used for styling and rendering diagrams.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the codebase.
- Ingestion points: The skill reads codebase files, project documentation, and Architectural Decision Records (ADRs) via the Explore sub-agent.
- Boundary markers: No specific delimiters or instructions are provided to the agent to treat codebase content as potentially malicious or to ignore embedded instructions.
- Capability inventory: The skill has the capability to write files to the temporary directory, update local project files (CONTEXT.md), and spawn multiple sub-agents to perform parallel analysis.
- Sanitization: There is no evidence of sanitization or escaping of the codebase content before it is processed by the agent or included in the generated HTML report.
Audit Metadata