sms-10dlc-registration
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (validate_10dlc_packet.py and validate_campaign_payload.py) to validate registration data. This is a primary function of the skill using the provided scripts and does not involve elevated privileges or remote downloads.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external JSON data for 10DLC compliance, including natural language fields such as message flows and sample messages. This represents a potential surface for indirect prompt injection if the processed data contains instructions designed to influence the agent's behavior.
- Ingestion points: External JSON files processed by scripts/validate_10dlc_packet.py and scripts/validate_campaign_payload.py.
- Boundary markers: The skill instructions rely on JSON schema structures but lack explicit delimiters or instructions for the agent to ignore embedded commands within text fields.
- Capability inventory: The skill uses local Python scripts for validation and requires the agent to translate data between different schemas.
- Sanitization: The validation scripts include regex-based sanitization for structured fields (EIN, email, phone, URLs), but natural language fields are only validated for string length and non-emptiness.
Audit Metadata