page-cro
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill instructions are focused on marketing analysis and do not contain any malicious patterns such as prompt injection, data exfiltration, or obfuscation.
- [NO_CODE]: The skill consists entirely of Markdown instructions and JSON metadata. It does not include any executable scripts (Python, JavaScript, or Shell) or binary files, which significantly reduces the potential attack surface.
- [SAFE]: The instruction in
SKILL.mdto read.agents/product-marketing-context.mdis a legitimate mechanism for retrieving project-specific context and does not involve unauthorized access to sensitive system configuration or credential files. - [SAFE]: While the skill is designed to analyze external content (marketing pages/URLs), which represents an indirect prompt injection surface, the skill definition itself does not include or request capabilities (such as network tools or command execution) that would allow an attacker to exploit this surface for malicious actions.
Audit Metadata