Bilibili Analytics
PassAudited by ClawScan on May 1, 2026.
Overview
The skill appears to do what it claims—scrape public Bilibili search results and generate local reports—but users should notice its browser automation and under-declared external tooling.
Before installing, make sure you are comfortable running local Bash/Python scripts and an external browser automation tool. Use small, intentional page counts, verify dependencies, and treat scraped titles/authors as data rather than instructions.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may open Bilibili pages and collect public video metadata for each requested page.
The script automates a browser and evaluates fixed JavaScript to scrape video cards across multiple pages. This is central to the stated analytics purpose, but users should notice the external-site automation and page-count-controlled loop.
for page in $(seq 1 $PAGES); do ... agent-browser open "$URL" ... DATA=$(agent-browser eval '...document.querySelectorAll(".bili-video-card")...')Use clear keywords, limit page counts, and respect Bilibili rate limits and terms.
Installation may require extra tools not visible in the registry capability declarations.
The installation guide references external tooling and a requirements file even though the registry metadata declares no required binaries or install spec. This is an under-declared dependency/provenance gap, not evidence of hidden behavior.
pip install -r bilibili-analytics/requirements.txt 2>/dev/null || true ... npm install -g agent-browser
Verify the source of agent-browser and any dependencies before installing, and update/confirm the metadata so required tools are explicit.