agent-reputation-benchmark

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses an external MCP server located at https://mcp.unifapi.com. It also recommends installation via 'npx skills add unifapi-agent/agents'. These resources are associated with the vendor's official domain and represent standard functional requirements for the skill.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and analyzes untrusted data from public real estate listings and user reviews.
  • Ingestion points: Public review text and business listing metadata retrieved from 'local/search' and 'maps/search' tools in the SKILL.md file.
  • Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious content within the ingested review text.
  • Capability inventory: The skill is configured for read-only operations and does not possess capabilities for file writing, system command execution, or network exfiltration.
  • Sanitization: There is no evidence of filtering or sanitization applied to the external review content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 10:29 AM
Security Audit — agent-trust-hub — agent-reputation-benchmark