tauri-native-api-integration
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The file
SKILL.mdcontains an instruction to executecat .claude/context/memory/learnings.mdas part of a mandatory memory protocol to maintain context between sessions. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading the contents of
learnings.mdwithout explicit boundary markers or sanitization. - Ingestion points:
.claude/context/memory/learnings.mdreferenced inSKILL.md. - Boundary markers: Not specified for the memory file content.
- Capability inventory: The skill has access to
Read,Write, andEdittools. - Sanitization: No explicit sanitization or validation of the memory file content is performed.
Audit Metadata