competitor-ad-research

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes sandbaseai-specific tools and a gateway (sandbase_describe_tool, sandbase_call_tool) to gather advertising data. No instances of credential harvesting, unauthorized network operations, or malicious command execution were detected. The skill instructions follow best practices for read-only research.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted content from external platforms. Ingestion points: Data returned by facebook_bulk_ads_library, dataforseo_v3_serp_google_organic_live_advanced, twitter_web_search_timeline, and instagram_v3_user_posts. Boundary markers: The instructions do not define specific delimiters for separating fetched data from the system prompt. Capability inventory: The skill is restricted to data synthesis and reporting, with no capabilities for file system modification, privilege escalation, or arbitrary code execution. Sanitization: No explicit filtering or sanitization of the retrieved data is specified. The risk is considered minimal given the lack of dangerous capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:31 PM
Security Audit — agent-trust-hub — competitor-ad-research