The Agent Skills Directory

[DATA_EXPOSURE_AND_EXFILTRATION]: The skill requires the agent to handle highly sensitive information, including PII (emails, names) and authentication secrets. Specifically, Step 2 instructs the agent to "Save one sample JWT or session cookie from the old system," which involves capturing active session material. The instructions also direct the agent to read the SCALEKIT_CLIENT_SECRET environment variable.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes untrusted data from legacy authentication systems during the audit and import phases.
Ingestion points: Data enters the agent context in SKILL.md (Step 2/3/4) and references/AUDIT-CHECKLIST.md when reading user profiles, organization metadata, and roles from source systems.
Boundary markers: None identified. There are no instructions to use delimiters or ignore embedded instructions within the source data.
Capability inventory: The skill uses @scalekit-sdk/node and cURL to perform network operations and data modification on the Scalekit platform.
Sanitization: There is no mention of sanitization or validation of the fields (like display_name or metadata) before they are passed to the SDK or API.
[COMMAND_EXECUTION]: The skill provides templates for executing shell commands via curl to interact with the Scalekit API and provides instructions to install the vendor-specific Node.js SDK using npm install.
[EXTERNAL_DOWNLOADS]: The instructions direct the agent to install the @scalekit-sdk/node package from the NPM registry if it is not already present in the repository.

migrate-to-saaskit