crawl-websites-at-scale
Fail
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for executing various CLI commands to manage Scrapy projects and run web crawlers.
- [COMMAND_EXECUTION]: The installation guide includes a command using
sudo(sudo apt-get install -y python3-pip) which grants administrative privileges for system-level package management. - [EXTERNAL_DOWNLOADS]: Recommends installing the
scrapyframework from external registries viapip. - [PROMPT_INJECTION]: Vulnerable to indirect prompt injection from untrusted web content. 1. Ingestion points: Processes HTML and XML data from arbitrary URLs via the
parsemethod. 2. Boundary markers: No delimiters or explicit safety instructions are defined to separate scraped content from agent instructions. 3. Capability inventory: Executes shell commands (scrapy crawl) and writes output to local files. 4. Sanitization: No validation or filtering is implemented to prevent scraped data from being interpreted as instructions.
Recommendations
- AI detected serious security threats
Audit Metadata