alicloud-solution-content-article-illustrator

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The run_workflow.py script orchestrates the workflow by executing sub-processes via subprocess.run. It calls local helper scripts such as load_preferences.py, build_outline.py, and collect_evidence.py, as well as an external image generation script within the same repository structure.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external Markdown content to generate prompts for AI image generation.
  • Ingestion points: Markdown articles read in scripts/run_workflow.py via the --source parameter.
  • Boundary markers: Not present; the skill lacks explicit delimiters or instructions to ignore potential commands embedded within the source article content.
  • Capability inventory: The skill possesses capabilities for subprocess execution and file system write operations.
  • Sanitization: Validation in scripts/validate_inputs.py is limited to verifying the file's existence and its extension.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:15 AM