ad-creative
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external files such as '.agents/product-marketing-context.md' and user-supplied performance data (CSV or pasted metrics). This data can influence the generation of ad content and the actions taken by campaign management tools.\n
- Ingestion points: Marketing context files and performance data provided during the ad generation loop.\n
- Boundary markers: The skill does not define explicit delimiters or security boundaries to isolate untrusted input from the agent's instructions.\n
- Capability inventory: The skill integrates with 'google-ads', 'meta-ads', 'linkedin-ads', and 'tiktok-ads' tools for managing campaigns.\n
- Sanitization: There is no evidence of input validation or sanitization before processing external data.\n- [EXTERNAL_DOWNLOADS]: The skill's reference materials suggest that users clone and execute code from third-party repositories.\n
- Evidence: Documentation points to the 'voicebox' GitHub repository and suggests using 'npx' to install 'remotion' components.\n- [COMMAND_EXECUTION]: The skill includes documentation and examples for running local CLI tools to interact with advertising platforms.\n
- Evidence: Example command provided: 'node tools/clis/google-ads.js reports get --type ad_performance'.
Audit Metadata