llm-mention-tracking

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on data aggregation and reporting using a specialized external API (unifapi.com). It utilizes standard OAuth for authentication, avoiding the need for hardcoded or sensitive credentials.
  • [SAFE]: Local persistence of tracking data is managed through project-specific configuration files (e.g., .agents/product-marketing.md), which is a benign and expected practice for maintaining historical trends.
  • [SAFE]: While the skill processes external data from AI answers, its capabilities are restricted to reporting and data visualization. It lacks high-risk execution tools (such as arbitrary shell commands or code evaluation) that would make it a significant target for indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 04:06 PM
Security Audit — agent-trust-hub — llm-mention-tracking