The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from cloud environment outputs and Infrastructure-as-Code (IaC) files, which creates a potential surface for indirect prompt injection. 1. Ingestion points: The agent reads external Terraform, CloudFormation, and Pulumi files using the Read tool and executes CLI commands whose output it then parses using the Bash tool. 2. Boundary markers: The instructions do not specify boundary markers or explicit warnings to ignore potential instructions embedded within the analyzed data. 3. Capability inventory: The skill utilizes Bash for command execution, Read for file access, and Write for report generation. 4. Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external audit sources before it is processed by the agent.

cloud-audit