web-search

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing tools and skills from the belt-sh and inference-sh repositories via npx and external URLs.\n- [COMMAND_EXECUTION]: The skill requires the Bash tool to execute belt CLI commands for searching and logging into the service.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the web that is subsequently used in LLM prompts, creating a surface for injection attacks.\n
  • Ingestion points: Data retrieved from external web search and extraction apps as shown in SKILL.md.\n
  • Boundary markers: The workflows use XML-style tags like to delimit data but lack explicit instructions to the LLM to ignore potential instructions within that data.\n
  • Capability inventory: The agent can execute shell commands using the belt CLI utility.\n
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the fetched web content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — web-search