local-competitor-scan

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to the UnifAPI MCP server (mcp.unifapi.com) to fetch live search and map data via OAuth. These are vendor-owned resources required for the skill's core functionality.
  • [COMMAND_EXECUTION]: The documentation provides instructions for installing the skill using npx and a plugin manager. These commands facilitate the deployment of the vendor's tools within the user's environment.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external search engine results and map listings, which presents a surface for indirect prompt injection.
  • Ingestion points: Untrusted data is retrieved through the local/search, maps/search, and seo/serp tool outputs as described in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore potentially malicious instructions embedded in the search results are provided.
  • Capability inventory: The skill is limited to analyzing data and generating markdown reports; it does not possess capabilities for file-system modification, subprocess execution, or arbitrary outbound network requests beyond the established tool definitions.
  • Sanitization: There is no instruction to sanitize or escape the content of the search results before including them in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 10:29 AM
Security Audit — agent-trust-hub — local-competitor-scan