test
v1.0.0Expert AI agent specializing in china e commerce operator. From The Agency (github.com/msitarzewski/agency-agents).
⭐ 0· 61·0 current·0 all-time
by@zhouqkt
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and included files (AGENTS.md, SOUL.md, IDENTITY.md, SKILL.md) consistently describe a China e-commerce operator role and related deliverables; no unexpected binaries, hosts, or credentials are requested.
Instruction Scope
SKILL.md defines the agent's identity, workflows, and campaign playbooks but does not instruct the agent to read local files, access system paths, call arbitrary external endpoints, or exfiltrate secrets. It asks the agent to 'remember' campaign data as role memory (agent-internal) rather than directing external collection of unrelated data.
Install Mechanism
No install spec and no code files are present; the skill is instruction-only so nothing will be written to disk or installed by the platform.
Credentials
The skill declares no required environment variables, credentials, or config paths. While real-world operation would need platform credentials to perform account actions, the skill itself does not request them—this is conservative and proportionate to an advisory/assistant role.
Persistence & Privilege
always:false and default invocation settings are used. The skill does not request persistent system presence or modification of other skills/configuration.
Assessment
This is an instruction-only agent describing e-commerce best practices and campaign workflows; it does not request credentials or install code. It appears safe and coherent with its stated purpose. Before giving it access to real platform accounts or sensitive data, remember: (1) you will need to supply platform credentials separately for any automated actions — only provide those to trusted code/services; (2) the agent's 'memory' means it may retain campaign details in your agent/session storage, so avoid sharing secrets (API keys, full account passwords) in prompts; and (3) the skill's source is listed as unknown in the registry metadata—if you plan to use it for account actions, consider verifying the original repository (github.com/msitarzewski/agency-agents) or testing in a sandbox account first.Like a lobster shell, security has layers — review code before you run it.
latestvk97d801zwn5rnthw9n1dxhrevx84k58j
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🛒 Clawdis