The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides functionality to retrieve and process transcription text from call recordings, which could contain malicious instructions embedded by external callers.
Ingestion points: Untrusted data enters the context via the transcription_text field in RecordingTranscriptionRetrieveResponse as shown in SKILL.md.
Boundary markers: The skill does not demonstrate the use of delimiters or explicit instructions for the agent to ignore potential commands within the transcription text.
Capability inventory: The skill has the capability to perform network API calls, delete resources (recordings, media, credentials), and modify configurations using the TelnyxClient.
Sanitization: There is no evidence of sanitization, filtering, or validation performed on the transcription data before it is processed.
[EXTERNAL_DOWNLOADS]: The skill references the official com.telnyx.sdk:telnyx Java SDK as a dependency for Maven and Gradle. This is a standard library provided by the vendor for service integration.
[COMMAND_EXECUTION]: The skill provides implementation examples for executing management commands against the Telnyx API, including deleting call recordings, dismissing log messages, and updating storage credentials.

telnyx-sip-integrations-java