google-ads-ad-copy
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, shell commands, or dangerous tool invocations that could be exploited.
- [SAFE]: No evidence of prompt injection, data exfiltration, or persistence mechanisms was detected during the analysis of the instructional content.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism to ingest external data but lacks dangerous capabilities to act upon it. 1. Ingestion points: Reads product marketing context from the .agents/product-marketing-context.md file. 2. Boundary markers: Not present. 3. Capability inventory: The skill is limited to text generation; it has no subprocess calls, file-write access, or network capabilities. 4. Sanitization: Not present.
Audit Metadata