onboarding-cro
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- PROMPT_INJECTION (SAFE): No attempts to override system instructions or bypass safety filters were detected. The instructions are focused on establishing a professional persona for user onboarding optimization.
- DATA_EXFILTRATION (SAFE): No network requests (curl, fetch, etc.) or hardcoded credentials were found. The skill references a local file
.agent/product-marketing-context.mdfor context, which is standard for agent-based workflows. - COMMAND_EXECUTION (SAFE): No shell commands, system calls, or script execution patterns are present in the skill.
- NO_CODE (SAFE): The skill consists entirely of markdown-based instructions and metadata. It does not include Python, JavaScript, or other executable scripts.
- INDIRECT_PROMPT_INJECTION (SAFE): While the skill ingests external data from context files, it lacks any functional capabilities (such as file-writing or network access) that could be exploited via malicious content in those files.
Audit Metadata