The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves scanning and transforming user-provided project source code, which creates a potential surface for indirect prompt injection if malicious comments or strings exist in the processed files.\n
Ingestion points: Project source code is read and analyzed by scripts/run-discovery.sh, scripts/scan-twilio-usage.sh, and scripts/scan-twilio-deep.py.\n
Boundary markers: Absent; the agent is directed to read and transform source files directly without specialized delimiters or instructions to ignore embedded natural language instructions.\n
Capability inventory: The skill utilizes capabilities to modify files (Phase 4) and perform network requests and command execution (Phase 5) during the migration process.\n
Sanitization: No specific sanitization or validation of the ingested code content is performed before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill orchestrates the migration through several bash and Python scripts that perform project analysis and testing.\n
The testing script scripts/test-migration/webhook-receiver.py executes shell commands via subprocess.Popen() to manage local testing environments.\n
Instructions require the agent to run various bash scripts with user-supplied arguments, such as the project root directory path.\n- [EXTERNAL_DOWNLOADS]: The skill guides the user to install dependencies from official software registries.\n
Recommends installation of the telnyx Python library and the @telnyx/webrtc Node.js library from their respective official registries. All downloads and URL references point to the vendor's verified domains and repositories.

telnyx-twilio-migration