ads
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a high-level guidance system for marketing tasks and does not execute dangerous shell commands or scripts.
- [EXTERNAL_DOWNLOADS]: The documentation safely references standard tracking scripts from well-known providers such as Google, Meta, LinkedIn, and TikTok. These are provided as implementation examples for users and are not executed by the agent itself.
- [PROMPT_INJECTION]: The skill ingests untrusted product marketing data from local files (e.g.,
.agents/product-marketing.md). While this provides an attack surface for indirect prompt injection, the skill lacks high-privilege capabilities such as arbitrary code execution or data exfiltration, rendering the risk negligible. - Ingestion points:
SKILL.mdreads context from.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md. - Boundary markers: Absent.
- Capability inventory: The skill is primarily focused on text generation for ad strategies and copy; it has no access to subprocesses or network exfiltration tools.
- Sanitization: No input validation is performed on the ingested context files.
Audit Metadata