sms
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documentation and referenced files provide legitimate business guidance regarding SMS strategy, platform selection (e.g., Klaviyo, Twilio, Postscript), and adherence to multi-jurisdictional regulations such as TCPA, GDPR, and CASL. No malicious scripts, hardcoded credentials, or exfiltration patterns were detected.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8) by directing the agent to incorporate external data into its context.\n
- Ingestion points: The skill instructs the agent to read local project context from files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md as mentioned in SKILL.md.\n
- Boundary markers: Absent. The instructions do not include delimiters or warnings to ignore embedded instructions within these ingested files.\n
- Capability inventory: No high-risk capabilities (subprocess execution, eval/exec, file writing, or direct network operations) are defined in the provided skill components.\n
- Sanitization: Absent. There is no mention of validating or escaping the content read from the external context files.
Audit Metadata