webtoon-orchestrator
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting external trend data and user-provided inputs to drive a multi-agent pipeline.
- Ingestion points: Trend research data and user-provided concepts.
- Boundary markers: No explicit delimiters are used to isolate untrusted research data.
- Capability inventory: The skill executes local shell scripts and performs file operations.
- Sanitization: Employs a multi-stage validation process with specialized agents to review outputs.
- [COMMAND_EXECUTION]: Orchestrates local shell commands for workspace management (mkdir, mv) and references a batch rendering script (scripts/codex_imagegen_batch.sh).
- [SAFE]: No evidence of credential theft, data exfiltration, or unauthorized remote code execution was found.
Audit Metadata