xiaohongshu-content-parser

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches images, videos, and avatars from remote URLs identified during the parsing process and saves them to a local media directory.
  • [DATA_EXFILTRATION]: The skill sends user-provided content URLs to the external service api.bugpk.com to retrieve post metadata. This is the core functionality and no private data is exfiltrated.
  • [COMMAND_EXECUTION]: A shell script is provided to execute the primary Node.js parsing script.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it processes and displays untrusted data from the Xiaohongshu API.
  • Ingestion points: API response fields including title and description in scripts/parse_xhs.mjs.
  • Boundary markers: Not present in the generated Markdown report.
  • Capability inventory: The skill can write files and perform network requests via fetch.
  • Sanitization: Filenames are sanitized via regex, but the report body content is not escaped.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 03:19 AM
Security Audit — agent-trust-hub — xiaohongshu-content-parser