cnki-parse-results

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements transparent JavaScript logic to parse academic metadata from a specific, well-known academic database (kns.cnki.net). The script uses standard DOM selectors like '.result-table-list' to extract publicly available information.- [COMMAND_EXECUTION]: The skill utilizes browser evaluation tools (browser action=act kind=evaluate) to execute JavaScript within the target page. The provided code is limited to data extraction and does not attempt to interact with the underlying system or sensitive browser data.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from search result pages.
  • Ingestion points: DOM scraping and accessibility tree snapshots via the browser tool (SKILL.md).
  • Boundary markers: None present.
  • Capability inventory: Browser navigation and JavaScript evaluation within the page context.
  • Sanitization: The skill uses .innerText and .trim() to extract textual data, minimizing the risk of executing scripts embedded in the scraped content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 12:19 AM
Security Audit — agent-trust-hub — cnki-parse-results