sms
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains instructions to read external context files from the project environment, which creates a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The skill instructs the agent to read context from files such as
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md(documented in SKILL.md). - Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions potentially embedded within these marketing context files.
- Capability inventory: The skill generates SMS marketing plans, flow designs, and copy, and provides platform and measurement recommendations.
- Sanitization: No explicit sanitization or validation mechanisms are mentioned for the content ingested from the external context files.
Audit Metadata