short-drama-write

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of story outlines and existing scripts, which is reflected in the agent's context during the writing and revision process.
  • Ingestion points: Narrative content is ingested from user-provided drama ideas, oral outlines, and existing Markdown files as specified in SKILL.md.
  • Boundary markers: The skill's instructions do not utilize explicit delimiters or 'ignore' instructions to isolate the untrusted drama content from the agent's system-level instructions.
  • Capability inventory: The skill possesses the capability to write files (e.g., episode cards, indices, and scripts) and execute local Python scripts (screenplay_index.py, voice_sheet_check.py).
  • Sanitization: No sanitization or safety filtering is applied to the ingested story text prior to processing by the agent.
  • [COMMAND_EXECUTION]: The skill relies on the execution of local Python utilities to maintain data integrity and generate derived indices. These scripts (screenplay_index.py and voice_sheet_check.py) are strictly focused on text processing, hashing for integrity, and file I/O using Python's standard library. They do not perform network operations or execute arbitrary shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 10:08 AM
Security Audit — agent-trust-hub — short-drama-write