before-after-ad
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected during the analysis of the skill's instructions and reference files. The skill functions as a structured creative guide for ad production, emphasizing claim substantiation and visual consistency.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as product facts and reference analyses, which constitutes a potential injection surface. However, the skill incorporates a mandatory human approval step and lacks high-risk capabilities like network access or arbitrary code execution, significantly mitigating the risk.
- Ingestion points: User-provided product facts, audience personas, and reference analysis notes in the 'Ground The Brief' workflow (SKILL.md).
- Boundary markers: Absent; the skill does not explicitly use delimiters or instruction-blocking prompts for user-provided context.
- Capability inventory: The skill is restricted to text generation and structured data handoff to downstream runners; it lacks subprocess execution, file-writing, or network operation capabilities.
- Sanitization: No explicit input validation, escaping, or filtering is performed on the ingested source context.
Audit Metadata