skills/unbrowse-ai/sites/carousell-sg/Gen Agent Trust Hub

carousell-sg

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect prompt injection surface because it fetches and processes external content from Carousell listings.
  • Ingestion points: Tools like carousell_sg__get_search_macbook_air and carousell_sg__read_page ingest data from carousell.sg.
  • Boundary markers: No specific boundary markers or delimiters for untrusted content are documented.
  • Capability inventory: The skill possesses capabilities to search, read, scrape, and perform browser-based actions via unbrowse.browse.act and unbrowse.run.
  • Sanitization: No sanitization or filtering of external data is specified before processing by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill documentation references the vendor's official domain (unbrowse.ai) for connecting to the MCP server and fetching skill configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 04:12 AM