ClawHub

find-package

v1.0.0

Help users locate their packages on delivery shelves by matching pickup codes to shelf photos. Trigger this skill when a user mentions finding packages, pick...

⭐ 0· 36·0 current·0 all-time
byfjh@noroot777
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
Name/description (find-package) match the contents: the skill needs image-processing (vision + a local Python script to draw boxes). The only declared runtime requirement is python3, which is appropriate for the included annotate.py script. No unrelated binaries or credentials are requested.
✓
Instruction Scope
SKILL.md instructs the agent to extract pickup codes from user-provided images, confirm the code with the user, run the local annotate.py to draw red bounding boxes, and send annotated images via the message tool. Instructions reference only images and pickup codes; they do not ask the agent to read unrelated files, environment variables, or external endpoints.
✓
Install Mechanism
No install spec (instruction-only) and only a small included Python script. The README notes a Pillow dependency (expected for image annotation). There are no downloads from external URLs or archive extraction steps.
✓
Credentials
Requires no environment variables or credentials. The skill references sending messages on Telegram via the platform's message tool, but it does not request any Telegram tokens or other secrets itself (that integration is expected to be provided by the host platform).
✓
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent privileges. It does not modify other skills or system-wide configuration. Autonomous invocation is allowed by default (platform behavior) but is not combined with any broad credential access.
Assessment
This skill appears coherent and contains only a local Python annotation script plus instructions to use the platform's vision capability and message tool. Before installing, confirm: (1) your OpenClaw environment provides the message/Telegram integration used to deliver results; (2) Pillow (pip3 install Pillow) is available if you want to run annotate.py locally; and (3) users understand they will be sending photos (privacy of images). If your environment requires explicit credentials to send Telegram messages, ensure those credentials are stored and granted by the platform rather than the skill itself.

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

latestvk97cgfryw63j84e3z9yqqxgcq983zaph

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

📦 Clawdis
Binspython3

Comments