minimax-web-search

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes external data from web searches, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Search result titles and snippets returned by the web_search tool (as defined in SKILL.md).
  • Boundary markers: Absent. There are no instructions or delimiters defined to separate untrusted search content from the agent's internal instructions.
  • Capability inventory: The skill facilitates network requests to an external API host ({api_host}/v1/coding_plan/search).
  • Sanitization: Absent. No evidence of content validation or sanitization for the retrieved snippets.
  • [No Code] (SAFE): The skill consists entirely of markdown documentation and metadata; it does not include executable scripts or binaries that could perform malicious actions directly.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 12:45 AM