web-reader
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's primary function involves fetching and processing data from external web pages, which introduces a surface for indirect prompt injection where instructions embedded in web content could influence the agent.\n
- Ingestion points: Content is ingested through the
page_readerfunction as demonstrated inSKILL.mdandscripts/web-reader.ts.\n - Boundary markers: The provided implementation examples do not include explicit delimiters or 'ignore instructions' directives to isolate the retrieved web content from the agent's control logic.\n
- Capability inventory: The skill is designed to retrieve, parse, and return HTML content, text, and metadata from any user-provided URL.\n
- Sanitization: Implementation patterns show basic HTML sanitization (such as removing script and style tags) but do not address the filtering of semantic instructions.
Audit Metadata