your-skill-name
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a structural template for affiliate marketing agents. It contains placeholders and guidance for developers but no active execution logic.
- [SAFE]: No remote code execution or suspicious network activity was identified. The provided GitHub link for issue reporting points to the author's own repository (Affitor).
- [PROMPT_INJECTION]: The skill contains instructional language for the agent (e.g., "Be pushy", "Do not flag this checklist to the user"), which are standard agent steering behaviors for this use case and do not constitute a safety bypass or jailbreak.
- [SAFE]: The skill processes user input via the defined 'Input Schema'. While this creates a surface for potential indirect prompt injection, the skill lacks any dangerous capabilities—such as file system writes, network requests, or subprocess execution—rendering the risk negligible.
- Ingestion points: Data enters via the
required_fieldandoptional_fielddefined in the Input Schema (SKILL.md). - Boundary markers: Absent in this template.
- Capability inventory: No active tool use, subprocess calls, or network operations are defined.
- Sanitization: Not specified in this documentation template.
Audit Metadata