juejin-article-trends
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Juejin API (titles, briefs, and author names) which is then presented to the agent. This creates a surface for indirect prompt injection where malicious instructions could be embedded in article content.
- Ingestion points:
scripts/juejin.jsfetches article rankings and categories fromapi.juejin.cn. - Boundary markers: The skill does not implement delimiters or specific instructions for the agent to ignore embedded commands within the fetched article data.
- Capability inventory: The script performs HTTPS GET requests and logs JSON output to the console. It does not perform file writes or local command execution.
- Sanitization: No sanitization or filtering is performed on the article titles or briefs before they are returned to the agent.
- [SAFE]: The script communicates with
api.juejin.cn, which is a well-known developer community platform. These network operations are limited to fetching public article trends and do not access sensitive local files or credentials.
Audit Metadata