Agency Role Match
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a coherent instruction-only role-selection workflow; its main thing to notice is that selected local role files can influence the agent’s later responses.
This skill appears safe to install as an instruction-only workflow. Before relying on it, make sure the local ~/.openclaw/agency-agents/ role files are from a source you trust, because the selected SOUL.md file will guide how the agent responds.
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.
The selected role file may change the agent’s tone, assumptions, and working instructions.
The skill intentionally loads persistent local role files and uses them to shape the agent’s behavior. This is aligned with the role-matching purpose, but those local role files can influence future output if their contents are inaccurate or unsafe.
根据用户选择，从 `~/.openclaw/agency-agents/[角色ID]/SOUL.md` 读取角色设定 ... 按照加载的角色SOUL.md，以该角色的身份、专业术语、沟通风格完成工作
Use role files from a trusted source, review unfamiliar SOUL.md files if needed, and keep the user’s current request and safety constraints above any role-specific instructions.