08-nghien-cuu-doi-thu

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official resources and integrations from Meta and Facebook, including the Facebook Ads Library (facebook.com/ads/library) and the Meta Official MCP (mcp.facebook.com/ads). These are well-known services used for legitimate market research and advertising analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as competitor websites, social media fanpages, and advertisement content.
  • Ingestion points: The agent is instructed to process content from user-provided URLs and data retrieved via the Facebook Ads Library MCP.
  • Boundary markers: While the skill provides structured templates for analysis, it does not explicitly define delimiters to isolate external content from instructions.
  • Capability inventory: The skill's primary function is data analysis and report generation in markdown format; it does not request or utilize high-risk capabilities such as arbitrary command execution, file system modifications, or unauthorized network operations.
  • Sanitization: The skill focuses on qualitative analysis (tone, hooks, USP) and does not currently implement specific filtering or sanitization of the external text it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:39 PM
Security Audit — agent-trust-hub — 08-nghien-cuu-doi-thu