The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it retrieves workspace configurations and variables from an external platform (HCP Terraform).
Ingestion points: Data is ingested through the get_workspace and list_workspaces tools defined in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores malicious instructions that might be embedded in workspace names or variable values.
Capability inventory: The agent has access to sensitive infrastructure operations, including create_workspace, delete_workspace, and trigger_run as listed in the tools section of SKILL.md.
Sanitization: No sanitization or validation mechanisms are described to mitigate risks from untrusted external data.

terraform-workspaces