markdown-to-storyboard

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the execute_code tool to run a Python script that writes the generated storyboard data to a local file named storyboard.csv using the standard csv library.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted markdown content provided by the user to generate the storyboard structure.
  • Ingestion points: The primary source of data is markdown text supplied by the user in Step 1 of the workflow.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands (like 'ignore previous instructions') are provided to the agent when it reads the source markdown.
  • Capability inventory: The agent has the capability to write files to the local file system using Python (execute_code).
  • Sanitization: The skill lacks explicit sanitization or validation logic to ensure that instructions embedded within the user-provided markdown do not influence the Python code generation template.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 01:57 PM