juejin-article-trends
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script
scripts/juejin.jsperforms HTTPS GET requests toapi.juejin.cnto retrieve article data and categories. This communication is required for the skill's primary functionality and targets a legitimate technical community platform.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the Juejin platform, including article titles and summaries.\n - Ingestion points: External article metadata is ingested via the Juejin API in
scripts/juejin.js.\n - Boundary markers: The skill does not use specific delimiters or instructions to ignore embedded commands within the fetched content.\n
- Capability inventory: The skill output is intended to be read and potentially summarized or acted upon by the AI agent.\n
- Sanitization: There is no sanitization of the external text content prior to it being formatted into Markdown or JSON.
Audit Metadata