audit

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to perform web searches on TikTok and Instagram to gather niche activity, search demand, and competitive data. These operations target well-known social media platforms and are essential for the primary purpose of social search auditing.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external web searches (TikTok/Instagram content) and user-supplied business information to generate an audit. This represents a vulnerability surface inherent to web-searching agents, but the rigid output framework and the specific nature of the data being analyzed minimize the risk of executing embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 05:12 AM
Security Audit — agent-trust-hub — audit