agentphone
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it ingests and processes untrusted external data.
- Ingestion points: The agent processes call transcripts (
transcriptfield) and incoming SMS message content (bodyfield) as described inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters provided in the prompt examples to distinguish between system instructions and untrusted data from calls/messages.
- Capability inventory: The skill allows the agent to place outbound phone calls, send SMS messages, and manage account resources using
curlcommands inSKILL.md. - Sanitization: No explicit sanitization or filtering of the transcript or SMS content is mentioned in the instructional logic.
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the AgentPhone API atapi.agentphone.to. These commands are used for standard telephony operations such as creating agents, buying numbers, and initiating calls.
Audit Metadata