08-nghien-cuu-doi-thu

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides structured templates and instructions for strategic competitive analysis and business positioning.
  • [EXTERNAL_DOWNLOADS]: It references official Meta/Facebook domains (mcp.facebook.com) for tool setup, which is recognized as a trusted and well-known technology service.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing external competitor data.
  • Ingestion points: External data retrieved from Facebook Ads Library MCP (SKILL.md).
  • Boundary markers: None present in the instructions.
  • Capability inventory: Textual analysis, content benchmarking, and SWOT report generation (SKILL.md).
  • Sanitization: No explicit sanitization or filtering of external tool outputs is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 09:26 AM
Security Audit — agent-trust-hub — 08-nghien-cuu-doi-thu