cnki-journal-index
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses standard browser automation to extract academic metadata from CNKI. It navigates to public URLs and uses JavaScript evaluation to parse specific DOM elements.- [PROMPT_INJECTION]: The skill ingests data from external web pages, creating a potential surface for indirect prompt injection.\n
- Ingestion points: The journal detail page is processed via
browser action=actinSKILL.md.\n - Boundary markers: Absent; scraped content is not delimited.\n
- Capability inventory: Browser navigation and DOM evaluation in
SKILL.md.\n - Sanitization: The script primarily uses specific CSS selectors to scope data extraction to relevant journal tags and information, which significantly reduces the ingestion of arbitrary page content.
Audit Metadata