paid-ads
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is composed exclusively of documentation and instructional templates (.md files). There are no scripts (.py, .js, .sh), configuration files that trigger execution, or binaries included.
- [PROMPT_INJECTION] (LOW): The skill instructs the agent to read a local context file at
.claude/product-marketing-context.md. - Ingestion Point: The AI agent is directed to read
.claude/product-marketing-context.mdat the start of the task. - Boundary Markers: Not present in the provided instructions.
- Capability Inventory: The skill provides strategy and copy generation; it mentions external tools (Google Ads MCP) but does not contain the code for them.
- Sanitization: None. While this is an indirect prompt injection surface, it is a standard mechanism for providing project context to AI agents and the severity is LOW as it only influences reasoning/output within the chat context without side effects in the provided files.
- [DATA_EXFILTRATION] (SAFE): No network operations, credential markers, or sensitive file access patterns (beyond the explicitly defined marketing context file) were detected.
Audit Metadata