HR ArchSystem
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a documentation-only HR design and evaluation skill with no code or install steps, but users should be careful because it may involve sensitive employee evaluation data.
This skill appears safe to install as an instruction-only HR reference. Before using it for real employee evaluations, ensure you have authorization to process the HR data, minimize or anonymize personal details, and keep any AI-generated recommendations subject to formal human review and appeal processes.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Employee names, performance records, project evidence, feedback, or AI tool usage details could be exposed if copied into prompts or shared reports without proper controls.
The evaluation workflow expects users to provide identifiable employee and performance evidence to the agent context. This is aligned with the HR evaluation purpose, but it is sensitive personal/workplace data.
**输入：** 被评价人信息、目标职级、行为证据、词典
Use only data the user is authorized to process, minimize and anonymize employee details where possible, redact sensitive logs, and avoid storing or sharing generated reports outside approved HR channels.
If an AI-generated evaluation is treated as final without human review, mistakes could affect compensation, promotion, or career development decisions.
The skill explicitly describes evaluation outputs being used for salary, promotion, and development decisions. This is purpose-aligned, and the artifacts include safeguards such as evidence, calibration, transparency, and appeal processes.
个人评价报告 → ① 薪酬调整依据 → ② 晋升决策依据 → ③ 个人发展计划（IDP）输入
Treat outputs as decision-support only. Require HR/manager review, evidence validation, calibration meetings, transparent criteria, and an appeal path before using results in employment decisions.