The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Terraform Registry, which constitutes a surface for indirect prompt injection if malicious instructions are embedded in provider or module documentation.
Ingestion points: External content is ingested through the get_provider_details and get_module_details tools described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or "ignore" instructions to separate the external documentation from the agent's system instructions.
Capability inventory: The skill is scoped to read-only registry operations including searching, listing versions, and retrieving metadata.
Sanitization: There is no evidence of sanitization, filtering, or validation of the documentation content fetched from the registry.

terraform-registry