web-scraper
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external URLs, representing a potential attack surface for indirect prompt injection.
- Ingestion points: Content is fetched from arbitrary URLs in
scripts/scrape.pyusing therequestslibrary. - Boundary markers: None. The scraped content is saved directly to files without specific markers distinguishing it as untrusted.
- Capability inventory: The skill performs network requests and writes to the local file system (specified in
scripts/scrape.py). - Sanitization: The script uses
BeautifulSoupto parse content and remove script/style tags, but does not filter the text content for potential injection attempts. - [COMMAND_EXECUTION]: The skill provides a Python script (
scripts/scrape.py) that performs network operations and file system writes based on user-provided arguments. This is the intended functionality of the tool and is implemented with safe filename sanitization.
Audit Metadata