roofline-perf
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to perform performance profiling and benchmarking by executing shell commands using the
taskCLI tool. These commands reference aTaskfile.ymllocated at${CLAUDE_SKILL_DIR}/../roofline-toolbox/Taskfile.yml, which is external to the skill package. - [NO_CODE]: The skill consists entirely of Markdown files providing instructions, tables, and reference data. It does not include any executable scripts, binaries, or source code, relying instead on pre-existing environment tools.
- [SAFE]: All external links point to reputable technology documentation and open-source project repositories. The skill follows standard practices for configuration (environment variables and
.envfiles) and does not exhibit any signs of obfuscation, exfiltration, or prompt injection.
Audit Metadata