tauri-app-clipboard
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading data from the system clipboard, which serves as an untrusted external input source that could contain malicious instructions.
- Ingestion points: The
readText()function demonstrated inexamples/usage.mdallows the agent to ingest arbitrary text from the clipboard into the application context. - Boundary markers: While
SKILL.mdmentions "safe copy, paste, and monitoring flows" and recommends restricting access to "user-initiated actions," the provided code examples do not demonstrate the use of delimiters or specific instructions to the agent to treat clipboard data as data rather than instructions. - Capability inventory: The skill utilizes the
@tauri-apps/plugin-clipboard-managerto perform read and write operations on the system clipboard. - Sanitization: The implementation examples lack explicit sanitization, filtering, or validation of the data retrieved from the clipboard before processing.
Audit Metadata