paid-ads
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read an external file for project context, creating a potential vector for indirect prompt injection if that file contains untrusted instructions.\n
- Ingestion points: The
SKILL.mdfile instructs the agent to read.claude/product-marketing-context.mdbefore asking clarifying questions.\n - Boundary markers: The instructions do not include boundary markers or explicit warnings for the agent to ignore any embedded commands within the ingested context file.\n
- Capability inventory: The skill references integrations with powerful advertising platforms (Google Ads, Meta, LinkedIn, TikTok) via MCP tools, which have the ability to manage campaign settings and spend budget.\n
- Sanitization: There is no specified logic to sanitize, validate, or filter the content of the ingested context file.
Audit Metadata