cs-import-codebase
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
codespringCLI to manage authentication, project linking, and the creation of feature maps and notes. These operations are essential for the integration with the vendor's platform. - [EXTERNAL_DOWNLOADS]: The skill is authorized to use
npx @codespring-app/cli, which fetches the official command-line interface from the npm registry. This is a standard and expected method for running the latest version of the vendor's tooling. - [PROMPT_INJECTION]: The 'Independent background audit' feature introduces an indirect prompt injection surface because it processes data from the user's codebase. Evidence Chain: (1) Ingestion points: All files in the local codebase and CodeSpring documentation. (2) Boundary markers: The audit sub-agent's instructions do not include specific delimiters or warnings to ignore instructions embedded in the analyzed code. (3) Capability inventory: The sub-agent has read access to the filesystem and the CodeSpring CLI. (4) Sanitization: No sanitization is performed on the code content before analysis. This risk is inherent to tools that perform automated code reviews.
- [DATA_EXFILTRATION]: The skill reads codebase structure, API routes, and database schemas to transmit them to the CodeSpring API. This data transfer is the primary purpose of the skill and is directed at the vendor's own infrastructure.
Audit Metadata