skills/varghq/skills/video-script/Gen Agent Trust Hub

video-script

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from a user-provided facts.md file. While this represents a surface for indirect prompt injection, the risk is mitigated by explicit instructions for the agent to verify all numbers and claims against the source file. The included scripts/check_script.py reinforces this by cross-referencing values in the script with the provided facts.
  • [DYNAMIC_EXECUTION]: The skill uses a Python script (scripts/check_script.py) to validate the generated scripts. This script uses only the Python standard library, performs static text analysis, and does not involve eval(), exec(), or any other dynamic code execution patterns that could be exploited.
  • [DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The skill operates locally on the files provided by the user and follows standard development workflows.
  • [REMOTE_CODE_EXECUTION]: The installation instructions utilize standard tools (npx, gh, claude) and point to the official vargHQ vendor repositories and domains, which is consistent with the skill's stated authorship and provides no evidence of unauthorized remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 09:49 PM