The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or suspicious data exfiltration techniques were detected. The skill utilizes legitimate Cloudflare Browser MCP tools to perform its stated functions.
[PROMPT_INJECTION]: The skill processes untrusted content from the internet, which presents a surface for indirect prompt injection.
Ingestion points: External web content is ingested through browser_markdown, browser_json, and browser_scrape tools defined in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the workflow.
Capability inventory: The skill's capabilities are restricted to browser-based interactions and do not include high-risk operations such as arbitrary command execution or access to sensitive system files.
Sanitization: The instructions recommend cleaning markdown by removing navigation and footer boilerplate, which aids readability but is not a security sanitization measure.

content-extractor