webcrawler-deep-crawl
What this skill does
Website deep crawl: extract content, metadata, and outbound links from websites for use in RAG pipelines, vector databases, and knowledge bases.
github/browser-act - Data Exfiltration - 5.3k stars
Threat analysis
Skill info
pkg:github/browser-act/skills@4577dc5?skill=webcrawler-deep-crawlAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/discover-llms-txt.py
The script fetches content from '/llms.txt' with `credentials: 'include'`, which may send cookies and authentication tokens to the server. This could lead to unintended data exfiltration if the serverData Exfiltration via local-llm-review
scripts/discover-sitemap.py
The script fetches content from '/sitemap.xml' and '/sitemap_index.xml' with `credentials: 'include'`, which may send cookies and authentication tokens to the server. This could lead to unintended datPrivacy Risk
Privacy Risk via local-llm-review
scripts/extract-page-content.py
The script extracts content from web pages and may include sensitive information (e.g., user-generated content, private emails, or personal data) in the output. If not properly sanitized, this could eBadge
Add the Anomity scan badge for webcrawler-deep-crawl to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of webcrawler-deep-crawl? Report an issue or request a rescan.
