training-srt-optimizer

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The documentation includes an installation command using npx that references the author's own GitHub repository (github.com/peter-tu-zynkr/zynkr-skill-builder). This is a legitimate vendor resource used for skill management.
  • [DATA_EXFILTRATION]: The skill's primary function includes uploading processed .srt files to a designated Google Drive folder (1ml0cPvrH5oohV36yqMMEqOrXXzW0ZVSf). This behavior is transparently documented and serves as the skill's intended output delivery mechanism.
  • [PROMPT_INJECTION]: The skill is designed to process external subtitle data, which represents an indirect prompt injection surface. However, the risk is effectively mitigated by strict instruction sets, a structured worksheet workflow, and automated validation checks that ensure the agent adheres to minimal, high-fidelity edits.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 01:36 AM
Security Audit — agent-trust-hub — training-srt-optimizer