skills/saliagadotcom/skills/pi-tui/Gen Agent Trust Hub

pi-tui

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a technical manual and reference for the pi-tui framework (@mariozechner/pi-tui). Analysis of the documentation and code examples found no evidence of malicious intent.\n- [COMMAND_EXECUTION]: The framework's autocomplete feature is documented to use external tools like fd for file system indexing and search, which is a standard functional requirement for TUI editors.\n- [PROMPT_INJECTION]: The framework includes components that ingest untrusted data, creating an indirect prompt injection surface.\n
  • Ingestion points: Editor, Input, and Markdown components in SKILL.md and reference/components.md accept external text content.\n
  • Boundary markers: None mentioned; the framework focus is on rendering and layout.\n
  • Capability inventory: The framework interacts with terminal I/O and local file system enumeration.\n
  • Sanitization: Provided utilities focus on layout constraints (width truncation) rather than security-oriented input filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 02:30 PM
Security Audit — agent-trust-hub — pi-tui