copywriting
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [SAFE] (SAFE): No malicious patterns, obfuscation, or dangerous capabilities were detected. The skill consists exclusively of markdown instructions for an AI agent.
- [Indirect Prompt Injection] (INFO): The skill ingests user-provided information during its context-gathering phase, which presents a surface for indirect prompt injection. Ingestion points: Phase 1 (Context Gathering) prompts users for audience, product, and context details. Boundary markers: Absent; inputs are directly integrated into the prompt flow. Capability inventory: None; the skill is limited to generating text copy and does not have access to file writing, network calls, or command execution. Sanitization: Absent; the skill relies on the agent's base safety layers. Given the lack of privileged capabilities, this is a negligible risk.
Audit Metadata