ad-creative
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external ad performance data (CSV, API output, or text) to iterate on creative variations, which represents an ingestion surface for potentially untrusted data.\n
- Ingestion points:
SKILL.md(Mode 2: Iterate from Performance Data).\n - Boundary markers: The skill does not explicitly define delimiters for untrusted performance data.\n
- Capability inventory: The skill utilizes tool integrations for Google Ads, Meta Ads, LinkedIn Ads, and TikTok Ads.\n
- Sanitization: No explicit sanitization or validation of the input data is described.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions for utilizing various third-party generative AI services and includes installation steps for an open-source tool (Voicebox). These are documented as standard resources for the skill's creative tasks.\n- [COMMAND_EXECUTION]: The documentation includes example CLI commands for interacting with ad platform APIs and setting up developer tools. These are illustrative of the intended operational workflow.
Audit Metadata