tauri-framework-upgrade
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external project configuration data, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill instructions direct the agent to read and analyze project files including
tauri.conf.jsonandcapabilities/default.json(referenced inSKILL.md). - Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard natural language commands that might be embedded within these configuration files.
- Capability inventory: The agent performs file reading and provides updated code/configuration mappings, which could lead to the generation of malicious code if the input files contain adversarial instructions.
- Sanitization: The skill does not implement or describe any validation or sanitization steps for the content of the files being processed.
Audit Metadata