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.mddirect the agent to read context from.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdat 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