game-sprite-pipeline

Fail

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The character generation logic is vulnerable to prompt injection attacks where an attacker can supply instructions instead of an image description to hijack the backend agent's execution flow. This occurs in sprite_generate.py when constructing prompts for the codex CLI.
  • [COMMAND_EXECUTION]: The pipeline invokes the codex CLI with the --dangerously-bypass-approvals-and-sandbox flag, which instructs the backend agent to execute shell commands without human approval or security sandboxing, enabling arbitrary command execution.
  • [DATA_EXFILTRATION]: Sensitive system data such as SSH keys and cloud credentials can be exfiltrated through the command execution vector, as sprite_generate.py captures and logs process output.
  • [COMMAND_EXECUTION]: Integration scripts such as road_to_aew_integration.py execute shell commands (npm run) in user-controlled directories, creating a risk of malicious script execution.
  • [EXTERNAL_DOWNLOADS]: The skill recommends and relies on external third-party dependencies such as the @openai/codex CLI and the rembg Python package.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 2, 2026, 04:39 AM
Security Audit — agent-trust-hub — game-sprite-pipeline