tzai-poster

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill searches for an executable named tzai-image within several predefined paths in the user's home directory (e.g., ~/.agents/skills/tzai-image/scripts/tzai-image). If found, it executes this script using bash to perform image generation tasks.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to download and install the required engine using npx skills add kedoupi/tzai-image-skill. This repository is owned by the same author as the skill.
  • [PROMPT_INJECTION]: The skill ingests user-provided text and interpolates it directly into a shell command via the --prompt "<user subject>" argument. This establishes an ingestion surface for indirect instructions or command injection, where the security relies on the sanitization capabilities of the underlying tzai-image engine script.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:50 AM
Security Audit — agent-trust-hub — tzai-poster