srt-translator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and formatting guidelines. No scripts, binaries, or executable commands were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting external data (subtitle files). Although this is an attack surface, the skill does not possess any dangerous capabilities like network access, file system writes, or command execution that could be triggered by malicious instructions embedded in subtitle text.
- Ingestion points: User-provided content pasted into the prompt as SRT, VTT, or TXT data.
- Boundary markers: The instructions recommend clear prompts such as 'Translate this SRT file to [Language]:' to separate instructions from data.
- Capability inventory: No tools, subprocesses, or network operations are requested or used.
- Sanitization: Standard LLM guardrails apply; the skill provides formatting checks but does not implement custom sanitization code.
Audit Metadata