bpmn-xml-generator
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted natural language process descriptions and directly interpolates this content into the documentation elements of the generated BPMN XML files. This creates a surface for indirect prompt injection where malicious instructions in the input could influence subsequent tasks or tools in an agentic workflow, such as the BPMN-to-PowerPoint skill mentioned in the instructions.
- Ingestion points: User-provided process descriptions during the clarification phases defined in SKILL.md.
- Boundary markers: There are no delimiters or warnings present to isolate user-supplied strings from the XML structural tags.
- Capability inventory: The skill instructions explicitly direct the agent to write files to the local directory (SKILL.md).
- Sanitization: The skill lacks any instructions for sanitizing, escaping, or validating user-provided text before it is embedded into the generated XML elements.
Audit Metadata