web-search

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior identified. The skill facilitates legitimate web search operations.
  • [COMMAND_EXECUTION]: Uses platform browser tools for navigation as intended. No execution of arbitrary or dangerous commands.
  • [DATA_EXFILTRATION]: Accesses well-known search engine domains to perform queries. No access to sensitive local environment data or credentials.
  • [PROMPT_INJECTION]: While the skill processes external web content, which is a common surface for indirect prompt injection, this is expected for a search skill and no exploitable capability abuse was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 11:49 AM