The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with the Replicas API endpoints as part of its primary functionality.
[DATA_EXFILTRATION]: The skill performs network operations to tryreplicas.com. This is the intended behavior for interacting with the Replicas service and uses an environment variable (REPLICAS_API_KEY) for secure authentication.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from API endpoints which creates an attack surface for indirect prompt injection.
Ingestion points: Data is fetched from <REPLICAS_API_URL_FROM_DOCS> using curl (SKILL.md).
Boundary markers: None present; the agent is instructed to process the raw output of the API call.
Capability inventory: The skill uses curl and jq to fetch and parse data.
Sanitization: No explicit sanitization or validation of the API response content is defined.

replicas