doppler-bench
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local benchmarking and utility scripts (e.g.,
tools/compare-engines.js,tools/vendor-bench.js) via Node.js and NPM. These operations are limited to the project's own directory and are consistent with its primary purpose of performance measurement. - [DATA_EXFILTRATION]: Benchmark results and artifacts are saved to a local directory (
benchmarks/vendors/results/). The skill does not contain instructions for transmitting this data to external or untrusted domains. - [SAFE]: The skill follows standard development practices for benchmarking, including the use of local configuration files and established Node.js runners. No evidence of prompt injection, obfuscation, or unauthorized credential access was found.
Audit Metadata