The Agent Skills Directory

[PROMPT_INJECTION]: The skill facilitates the ingestion of data from external and internal Vault API endpoints, creating a potential surface for indirect prompt injection if the returned data is malicious or untrusted.
Ingestion points: Data returned from Vault REST API calls (e.g., KV secret reads, health checks) as described in SKILL.md.
Boundary markers: None present; the instructions do not include delimiters or warnings to the agent regarding the processing of embedded instructions in the API output.
Capability inventory: The skill utilizes curl for network requests, jq for JSON processing, and kubectl for token generation.
Sanitization: There is no evidence of sanitization or validation logic for the data retrieved from the API endpoints.

vault-api