suede-sms
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external project context files, which presents a surface for indirect prompt injection. \n
- Ingestion points:
SKILL.mdinstructs the agent to read.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md. \n - Boundary markers: The instructions do not specify any delimiters or safety warnings to distinguish between user-provided context and system instructions. \n
- Capability inventory: The skill is capable of drafting SMS marketing messages, designing sequences, and recommending platforms. \n
- Sanitization: No sanitization or validation logic is defined for the ingested context data.
Audit Metadata