embed-subtitles
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using
npx ts-nodefor video rendering andpython3 -cfor subtitle processing. - [DYNAMIC_EXECUTION]: A multi-line Python script is defined in the instructions to be executed at runtime to modify subtitle files, which involves file I/O and regex operations.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The agent is instructed to read and translate the content of external SRT files, which are controlled by users or third parties.
- Boundary markers: There are no explicit instructions or delimiters to protect the agent from interpreting content within the SRT files as instructions.
- Capability inventory: The skill possesses the ability to read from and write to the local file system and execute system commands (
ffmpeg,python3). - Sanitization: No sanitization logic is present to filter out potentially malicious text or commands embedded within the processed subtitle data.
Audit Metadata