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
npxthat 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
.srtfiles 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