tts-script-generator

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Python script located at scripts/generate.py which is executed locally to process Markdown files. This script utilizes standard Python libraries (re, json, argparse) for text cleaning and segmentation tasks. No suspicious system calls or external network requests are made by the script.- [PROMPT_INJECTION]: The skill processes user-supplied documents which creates a surface for indirect prompt injection. \n
  • Ingestion points: The skill reads markdown files via the Read tool or command-line arguments in generate.py.\n
  • Boundary markers: The instructions do not define explicit delimiters for untrusted content within the AI prompts.\n
  • Capability inventory: The skill has access to tools like Bash, Read, Write, and Edit.\n
  • Sanitization: A clean_markdown function is present to strip formatting, though it does not filter for instructional content.- [SAFE]: No obfuscation, hardcoded credentials, data exfiltration, or persistence mechanisms were detected in the skill instructions or associated script.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 09:19 PM