light-file-reading
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs file analysis using standard libraries and external tools. No malicious behavior was identified during the analysis.
- [COMMAND_EXECUTION]: The instructions guide the agent to use established command-line utilities such as
ffmpeg,pandoc, andLibreOfficefor file processing tasks. This usage is consistent with the skill's primary function. - [EXTERNAL_DOWNLOADS]: The skill references several external libraries and repositories from trusted organizations, including Microsoft and Anthropics. These references are used for documentation and dependency management purposes.
- [PROMPT_INJECTION]: The skill contains logic to handle indirect prompt injections by treating all input from files as data rather than instructions, and it specifically instructs the agent to report detected injection attempts.
- [SAFE]: The dynamic import pattern (
importlib.import_module) detected in the scripts is used for lazy-loading hardcoded, legitimate libraries, which is a benign implementation.
Audit Metadata