sms

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's instructions and reference files are purely informative and educational. They focus on providing high-quality marketing strategy, ensuring compliance with international regulations (LGPD, TCPA, GDPR, CASL), and advising on the use of well-known third-party SMS platforms such as Klaviyo, Twilio, and Postscript. No evidence of shell command execution, sensitive file access, or unauthorized network operations was found.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a standard functional design to read external context files to tailor its advice to a specific business.
  • Ingestion points: Instructions in SKILL.md direct the agent to read context from .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md at the start of an interaction.
  • Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following potential commands embedded within these context files.
  • Capability inventory: The skill's functionality is limited to generating text-based marketing plans, copywriting, and strategy recommendations. There are no identified capabilities for performing dangerous actions like writing files, executing shell commands, or making network requests.
  • Sanitization: There are no explicit sanitization or validation routines described for the ingested content, relying instead on the platform's default safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 10:25 PM