anti-slop-document-editing
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script (
scripts/ste_lint.py) designed to identify writing patterns such as long sentences, passive voice, and marketing jargon. The instructions direct the agent to execute this script usingpython3on provided drafts. The script logic is entirely local, using standard regular expressions to process text without accessing the network or sensitive system files. - [EXTERNAL_DOWNLOADS]: The reference file
references/s1000d-research-basis.mdcontains links to technical documentation standards websites (e.g., s1000d.org, dla.mil, asd-ste100.org). These URLs are provided for human context and informational research; the skill does not automate downloads from these sources or execute remote code. - [DYNAMIC_EXECUTION]: The test suite (
tests/test_ste_lint.py) utilizesimportlibto dynamically load the linter script for verification. This is a standard practice for unit testing Python utilities and is restricted to the skill's own internal file structure.
Audit Metadata