paid-ads
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional content and configuration files focused on performance marketing. No indicators of prompt injection, credential theft, or remote code execution were identified across the 5 analyzed files.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection, which is inherent to its functionality of ingesting user data to perform marketing tasks.
- Ingestion points: User-provided inputs regarding campaign goals, product details, and audience information as requested in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the user-provided data.
- Capability inventory: The skill references integrations with external advertising tools (Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads) as described in the 'Tool Integrations' section of
SKILL.md. - Sanitization: There are no documented sanitization or validation protocols for processing external data within the skill's instructions.
Audit Metadata