memory-benchmark
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run benchmarks using
cargo run --release -p memory-benchmark. This is a standard command for executing a local Rust package to collect performance data.\n- [COMMAND_EXECUTION]: The skill references a local Python scriptpython3 perf/memory/analyze-dhat.pyused to process benchmark results stored in a local JSON file. This is routine data processing within a development environment.\n- [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized remote code execution was found. The skill operations are correctly scoped to local performance benchmarking.
Audit Metadata