Item manager

v1.0.0

自动识别物品存放位置,支持保质期、过期提醒、自动分类、LLM名称校验,不自动修改名称,确认后才更正,简洁好用

1· 54·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (item location, expiry, classification, LLM name-check) match the declared dependencies (filesystem, memory, llm). No unrelated binaries, credentials, or config paths are requested.
Instruction Scope
SKILL.md contains only natural-language handling rules and examples for recording/querying items. It relies on the agent's memory/filesystem to store records and the LLM capability to validate names. This is coherent, but implies user data (item names, locations, expiry dates) will be written to agent storage and sent to the LLM for validation.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing is downloaded or written by an installer, which minimizes supply-chain risk.
Credentials
No environment variables, credentials, or external endpoints are requested. The only sensitive operations are use of LLM and persistent memory/filesystem, which are appropriate for the described features.
Persistence & Privilege
always:false and default autonomous invocation are set; the skill does not request permanent system-wide privileges or to modify other skills. Its need to write/read memory/filesystem is expected for its purpose.
Assessment
This skill appears internally consistent and lightweight, but it will store item names, locations, and expiry dates in the agent's memory/filesystem and will use the agent's LLM to validate names. Before installing, decide whether you are comfortable with those records being stored and processed by your agent/model. Ask or check: which model is used for name validation, where the data is stored, retention policy, and whether stored items are shared outside your account. If you have sensitive items, test with non-sensitive examples first. The skill has no external code to review beyond SKILL.md/README and the source is listed as unknown — that is normal for instruction-only skills but means there is no additional code to audit.

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

latestvk9739r8d4rh0jvk2f65gd9xd9n84cv2b

License

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

Comments