Based on the description, it is inferred that the injection can be performed remotely. The sanitization routine fails to properly validate or escape characters supplied in the prompt description field, allowing an attacker to inject malicious payloads. The description does not explicitly state that the injection enables arbitrary code execution; however, it indicates that a public exploit exists, suggesting that the injected payload is eventually processed by the bot or its skills in a way that may lead to unintended behavior.

The affected product is AstrBotDevs AstrBot 4.23.6. No other versions are mentioned in the CNA data, so only this specific build should be considered at risk. Systems running this version without a patch remain vulnerable.

With a CVSS score of 5.3 the vulnerability is considered moderate, and the lack of an EPSS score does not diminish the fact that a publicly available exploit has been released. Based on the description, it is inferred that the attack can be carried out from remote without authentication by supplying a crafted prompt description. The vulnerability is not listed in the CISA KEV catalog, but the public nature of the exploit and vendor non‑responsiveness increase the urgency of remediation.