Agent Discovery

v1.0.0

Agent发现探索助手。搜索、评估、集成公开Agent。使用场景:(1) 搜索可用Agent,(2) 评估Agent能力,(3) 集成方案设计,(4) 成本效益分析。

0· 23·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
The name/description (Agent discovery and evaluation) matches the SKILL.md examples. The skill declares no binaries, env vars, or config paths — which is appropriate for a purely advisory/search helper.
Instruction Scope
SKILL.md contains only high-level examples of user prompts (search, compare, integration design, cost analysis). It does not instruct the agent to read files, access credentials, call external endpoints, or exfiltrate data.
Install Mechanism
No install specification and no code files are present. As an instruction-only skill, it does not write code to disk or download artifacts.
Credentials
No environment variables, credentials, or configuration paths are required — proportional to the stated advisory/search purpose.
Persistence & Privilege
always is false (not force-included). The skill does not request persistent system modifications or access to other skills' configs. Normal autonomous invocation remains possible but is not excessive here.
Assessment
This is an instruction-only, advisory skill and appears coherent. Proceeding to install poses minimal direct risk as-is. Before trusting future versions, review any added install steps, requested environment variables/credentials, or changes that would enable network downloads or persistent configuration; if you allow autonomous invocation, be aware the agent could use the skill without prompting, so restrict that if you prefer manual control.

Like a lobster shell, security has layers — review code before you run it.

latestvk972a9sety5ytfcdz1aq6vnbvn84kjhb

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments