processon-diagram-generator
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands for version checking (curl) and core logic processing (python3 scripts/processon_api_client.py).
- [EXTERNAL_DOWNLOADS]: Fetches version metadata from a public GitHub repository (processonai/processon-skills) to facilitate updates.
- [DATA_EXFILTRATION]: User-provided text and image content are sent to ProcessOn's API endpoints (smart.processon.com) for processing, which is the declared primary function.
- [PROMPT_INJECTION]: Contains a surface for indirect prompt injection via user-supplied prompts and sketches. Ingestion points: User text prompts and uploaded images/sketches (SKILL.md). Boundary markers: Absent. Capability inventory: Execution of shell commands (SKILL.md). Sanitization: No evidence of sanitization for user input used in script execution.
Audit Metadata