tauri-app-file-system
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its use of templates.\n
- Ingestion points: The
templates/basic.mdfile defines placeholders such as{app_data_dir},{download_dir},{readonly_paths}, and{write_paths}that are intended to be populated with user-supplied data.\n - Boundary markers: The skill lacks explicit instructions or delimiters to isolate these interpolated values or warn the agent to ignore instructions embedded within the provided data.\n
- Capability inventory: The skill provides instructions and examples for file system operations including reading, writing, and directory management via the
@tauri-apps/plugin-fsplugin.\n - Sanitization: There are no documented procedures or instructions for the agent to sanitize or validate the input data before it is interpolated into the configuration template.
Audit Metadata