short-drama-write

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill uses local Python scripts to process script data for duration estimation and scene indexing. These scripts perform static analysis on the text content.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using python3 to run the provided analysis tools (scripts/screenplay_index.py, scripts/duration_estimate.py).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of script drafts and outlines, which are then passed to the analysis scripts.
  • Ingestion points: User-provided script content and outlines in the conversation context.
  • Boundary markers: The skill uses standard Markdown scene headers and dialogue syntax to delimit content.
  • Capability inventory: Access to shell command execution (python3) and local file system operations (read/write) via the provided scripts.
  • Sanitization: Content is parsed using regular expressions in the Python scripts to identify structural elements without executing the content itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 03:46 PM
Security Audit — agent-trust-hub — short-drama-write