The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from SMS and voice transcripts which represents a surface for indirect prompt injection attacks. * Ingestion points: Data enters the agent's context through the smsInboxList and smsInboxGet methods, and the transcript and summary outputs from the agent.voice tool. * Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore commands within the received content. * Capability inventory: The skill possesses the capability to send SMS and initiate autonomous voice calls using the @oneshot-agent/sdk package. * Sanitization: There is no evidence of sanitization or validation of external content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill utilizes the @oneshot-agent/sdk Node.js package to facilitate its core messaging and voice functionality. This package is a vendor-owned resource associated with the skill's author.

oneshot-messaging