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, andinstagram_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