generate-workflow-diagram
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill extracts diagram labels and source information from external files, creating a surface for indirect prompt injection.
- Ingestion points: Source files in the
./src/directory are read using theput()andput_auto()functions inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions potentially embedded within the source file annotations.
- Capability inventory: The skill possesses capabilities to write to files (
writeLines()) and output content to the console (cat()), which could be used to propagate malicious payloads. - Sanitization: There is no evidence of sanitization or validation of the extracted annotation text before it is interpolated into the Mermaid flowchart output.
Audit Metadata