article-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
Bashto execute local Python scripts (mql5_extract.py,official_docs_extractor.py) and shell scripts (extract_all_python_docs.sh) within a defined working directory ($HOME/eon/mql5). These commands are used for their primary purpose of data extraction and processing. - [EXTERNAL_DOWNLOADS]: The skill uses
curlto fetch documentation pages frommql5.com. This is within the stated primary purpose of the skill and targets a well-known technical resource. - [INDIRECT_PROMPT_INJECTION]: The skill processes external HTML data from
mql5.comto convert it to Markdown. While this is an ingestion surface, the skill implements strict domain bounding rules (onlymql5.com) and uses specialized extractors, reducing the surface for unintended instruction execution.
Audit Metadata