google-ads-experiments
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read an external context file at
.agents/product-marketing-context.mdif it exists. This serves as an ingestion point for untrusted data which could theoretically contain malicious instructions. - Ingestion points: SKILL.md (Check for product marketing context first section).
- Boundary markers: None present for the external file content.
- Capability inventory: None. The skill does not define or use any tools, shell commands, or network operations.
- Sanitization: None.
Audit Metadata