customer-persona

Warn

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install a third-party CLI tool using npx skills add belt-sh/cli and references installation instructions hosted at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. These sources and the associated inference.sh service are not recognized as trusted vendors or well-known services, posing a supply chain risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external search services, which are potentially attacker-controlled.
  • Ingestion points: Data from external search assistants (tavily/search-assistant, exa/search, and exa/answer) is retrieved and processed by the agent via the belt CLI tool (SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or provide guidance to the agent to ignore instructions embedded in the external data.
  • Capability inventory: The skill uses Bash(belt *) to execute CLI commands and interact with remote services.
  • Sanitization: Absent. There is no evidence of filtering, escaping, or validation of the data retrieved from external sources before it is interpreted by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 21, 2026, 08:14 PM
Security Audit — agent-trust-hub — customer-persona