The Agent Skills Directory

[COMMAND_EXECUTION]: The skill orchestrates the migration by executing several local bash and Python scripts included in the package to perform project discovery, code linting, and validation.
Evidence: SKILL.md directs the agent to execute bash {baseDir}/scripts/run-discovery.sh <project-root> and bash {baseDir}/scripts/run-validation.sh <project-root>.
[EXTERNAL_DOWNLOADS]: The skill instructions automate the installation of dependencies using package managers (pip, npm, gem, go get) and communicate with the Telnyx API.
Evidence: SKILL.md Phase 3.2 provides commands for installing the telnyx SDK across multiple languages.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the user's existing source code during the discovery and migration phases.
Ingestion points: Project files scanned by run-discovery.sh and read by the agent in Phase 4.
Boundary markers: Absent; the agent is not instructed to use specific delimiters or ignore instructions embedded in the project files.
Capability inventory: The skill has extensive permissions including file system modification, shell command execution via bash, and network access via curl.
Sanitization: Absent; the instructions do not specify any validation or sanitization of the content read from the project files.
[CREDENTIALS_UNSAFE]: The skill explicitly asks the user to provide their TELNYX_API_KEY during the prerequisite phase.
Evidence: SKILL.md Step 0.1 requests the user's API key to initialize the migration state.

telnyx-twilio-migration