onboarding
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of instructional markdown and reference materials for marketing strategy. It does not contain any executable scripts, shell commands, or obfuscated content.
- [NO_CODE]: No Python or Node.js code is present in the skill, precluding risks related to remote code execution or malicious scripts.
- [PROMPT_INJECTION]: The skill instructs the agent to read local marketing context files (e.g., .agents/product-marketing.md) to tailor its advice. While this represents a surface for indirect prompt injection, the risk is negligible as the skill lacks high-privilege capabilities. 1. Ingestion points: Marketing context files specified in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Limited to text-based advice and internal reference reading. 4. Sanitization: Absent.
Audit Metadata