simplified-technical-english
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-supplied technical documents, creating a potential surface for indirect instructions hidden in source material. 1. Ingestion points: Procedural, descriptive, and safety instructions provided for STE processing. 2. Boundary markers: The skill employs explicit selection markers (
STE:START/STE:END) and preservation ledgers to define the scope of rewritten content. 3. Capability inventory: Agent executes local Python diagnostics for surface-level rule checks. 4. Sanitization: Instructions require character-for-character preservation of machine-readable literals, code, and identifiers. - [COMMAND_EXECUTION]: The skill utilizes local Python scripts (
scripts/analyze_ste_surface.py) for word counting and structural analysis. These tools use standard libraries to perform text processing within the local environment and do not involve network operations or privilege escalation. - [EXTERNAL_DOWNLOADS]: The skill references official documentation and links to the ASD-STE100 organization and the AeroSpace and Defence Industries Association of Europe (ASD) for compliance verification and resource acquisition.
Audit Metadata