IG Cropper
v1.3.0Transforms cluttered Instagram mobile screenshots into clean, distraction-free architectural and design references. Use when you need to automate the extract...
⭐ 0· 98·0 current·0 all-time
by@yfxa
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the included Python script and instructions: the tool detects Instagram dark‑mode background rows and crops the largest non‑background block. No unrelated capabilities (cloud access, system config, extra tooling) are requested.
Instruction Scope
SKILL.md instructs running the included script with local input/output paths and lists Pillow as the only dependency — that is consistent. Minor implementation bug: the script samples pixels every 10 columns and divides by (w // 10); very narrow images (width < 10) could cause a division-by-zero error, but this is a robustness/bug issue, not malicious behavior.
Install Mechanism
Instruction-only skill with no install spec; dependency is Pillow (pip). No downloads from external URLs or archive extraction occur.
Credentials
The skill requires no environment variables, credentials, or config paths. The code performs only local file I/O on the specified input/output image paths.
Persistence & Privilege
always: false and no persistence or self-modification is requested. The skill is user-invocable and will not be force-enabled or request elevated platform privileges.
Assessment
This skill appears coherent and safe for local use: it only reads an input image and writes a cropped output, with no network access or credential use. Before running, install Pillow (pip install pillow). Be aware of a minor bug with very narrow images (width < 10) that may crash the script; if you rely on many input sizes, test on sample images or add a guard in the code (e.g., ensure denominator > 0). If you process sensitive images, run the script locally or in an isolated environment since the skill does not include explicit data‑exfiltration protections, even though the provided code makes no external network calls.Like a lobster shell, security has layers — review code before you run it.
latestvk97d5wnbhw070t5p97v5md9xgh8391xe
License
MIT-0
Free to use, modify, and redistribute. No attribution required.