skills/actvox/marketingskills/sms/Gen Agent Trust Hub

sms

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional markdown and reference files providing guidance on SMS/WhatsApp marketing, including sequences, compliance, and platform selection. No malicious code, prompt injections, or obfuscation techniques were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external business context from local files. Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md. Boundary markers: None present. Capability inventory: Strategic planning and copy generation (no high-risk tool usage or filesystem writes). Sanitization: None present. This represents a standard context ingestion surface for an AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 07:40 PM