paid-ads
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of informational markdown and reference templates for performance marketing. No malicious patterns, command execution, or network exfiltration were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest project-specific context from a local file, which is a standard pattern for context-aware agents. * Ingestion points:
SKILL.md(instructions to read.claude/product-marketing-context.md). * Boundary markers: None specified. * Capability inventory: The skill references MCP tools for managing advertising accounts on platforms like Google, Meta, and LinkedIn as listed inSKILL.md. * Sanitization: None specified.
Audit Metadata