stac-screen-builder
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python scripts,
scripts/new_screen.pyandscripts/new_theme_ref.py, which are designed to create directories and write files to the local file system. These operations are essential to the skill's purpose of scaffolding project files. - [INDIRECT_PROMPT_INJECTION]: The skill generates source code based on user-provided inputs, presenting a surface for indirect injection.
- Ingestion points: Screen and theme identifiers provided as command-line arguments to the Python scripts.
- Boundary markers: User-supplied values are interpolated into templates without specific security delimiters, although they are primarily used in identifier contexts.
- Capability inventory: The scripts possess file system write and directory creation capabilities.
- Sanitization: The scripts implement rigorous input validation using regular expressions (e.g.,
[a-z][a-z0-9_]*) to ensure that user-provided names do not contain malicious characters or injection payloads.
Audit Metadata