The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external process descriptions and XML content, which represents a potential attack surface for indirect prompt injection.
Ingestion points: The skill accepts untrusted data in the form of 'Process description in natural language' and 'BPMN XML content' as shown in the usage section of SKILL.md.
Boundary markers: The usage examples do not demonstrate the use of delimiters or boundary markers to isolate user-provided data from system instructions.
Capability inventory: The skill frontmatter grants access to the Bash tool, which is a high-capability execution environment.
Sanitization: No sanitization, validation, or escaping mechanisms for the input data are described in the instructions.

bpmn-generator