tweet-series-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external X/Twitter pages. * Ingestion points: Tweet content and profile pages are retrieved via
mcp__claude-in-chrome__get_page_textandmcp__claude-in-chrome__read_page(SKILL.md). * Boundary markers: The instructions do not specify boundary markers or 'ignore instructions' warnings for the scraped content. * Capability inventory: The skill uses browser automation tools to navigate, read pages, and execute JavaScript. * Sanitization: There is no explicit sanitization or filtering mentioned for the external content before it is processed into the final JSON structure. - [DYNAMIC_EXECUTION]: The skill uses a JavaScript tool to extract links from the browser context. * The JavaScript snippet
document.querySelectorAll('article a').forEach(...)is used to programmatically collect URLs from the DOM (SKILL.md). * This execution is limited to the browser tab environment for data extraction purposes.
Audit Metadata