textual-event-messages
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a TUI interface that ingests untrusted user input while having access to the Bash tool, creating a surface for indirect prompt injection.
- Ingestion points: User input is ingested via the
Inputwidget in theCommandWidgetclass within Example 1 (SKILL.md). - Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted input from agent instructions.
- Capability inventory: The skill has access to the
Bash,Read,Write, andEdittools as specified in theallowed-toolsmetadata. - Sanitization: There is no evidence of input sanitization or validation logic in the provided code snippets.
Audit Metadata