get-feed-detail-skill

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted external content. \n
  • Ingestion points: The script scripts/get-feed-detail.mjs retrieves feed details and user comments from the Xiaohongshu platform via an HTTP-based MCP server. \n
  • Boundary markers: There are no boundary markers or 'ignore' instructions used in the code or prompt to separate retrieved data from agent instructions. \n
  • Capability inventory: The skill is intended to run via Bash, and the agent environment includes Bash and Read tools, which could be exploited if malicious instructions are processed. \n
  • Sanitization: The script returns the raw JSON content of the feed without any sanitization or filtering of the text content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:25 AM