cloudbase-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is analyzing untrusted project code, which serves as a vulnerability surface for indirect prompt injection. -- Ingestion points: Project source files (.ts, .tsx, .js, .jsx, .html, .sql, .json) read in the project directory. -- Boundary markers: Absent; there are no explicit delimiters or instructions to ignore commands within the analyzed code. -- Capability inventory: Local file system read access and provision of a linting script for manual user execution. -- Sanitization: Absent; code is analyzed in its raw form without filtering. -- Mitigation: Add explicit instructions to the agent to ignore any natural language instructions or overrides found within comments or string literals of the code being reviewed.
- [COMMAND_EXECUTION]: The skill provides a Node.js linting script and instructs users to manually execute it. The source code for the script is transparently provided in the documentation for review prior to execution.
Audit Metadata