llm-mention-tracking

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches marketing and search data from the vendor's official UnifAPI infrastructure at https://mcp.unifapi.com. This is an expected behavior for the skill's purpose and involves authorized vendor resources.
  • [PROMPT_INJECTION]: The skill processes data from external AI search engines, creating a surface for indirect prompt injection. * Ingestion points: Data retrieved via the unifapi tool's geo/mentions/search and geo/serp endpoints. * Boundary markers: Absent; no specific instructions are provided to the agent to treat the external search results as untrusted content. * Capability inventory: The skill performs network reads via tools and is instructed to maintain local records for trend tracking. * Sanitization: No explicit sanitization or filtering of the retrieved content is defined before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 10:29 AM
Security Audit — agent-trust-hub — llm-mention-tracking