paid-ads
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown documentation and templates, with no executable scripts or code provided in the analyzed files.
- [PROMPT_INJECTION]: The instructions do not contain behavior-overriding patterns, safety bypasses, or instructions to reveal system prompts. It includes a surface for indirect prompt injection via the ingestion of the .claude/product-marketing-context.md file, which is used to provide task-specific marketing context. 1. Ingestion points: .claude/product-marketing-context.md (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Integration with ad platform MCP tools (SKILL.md). 4. Sanitization: No explicit sanitization or validation of the context file content is performed.
- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path access (outside of intended context files), or unauthorized network operations were detected.
- [REMOTE_CODE_EXECUTION]: No patterns for downloading or executing remote scripts or unverified dependencies were identified.
- [COMMAND_EXECUTION]: No dangerous system commands, privilege escalation attempts, or persistence mechanisms were found.
Audit Metadata