Prompt injection

Prompt injection

Description

The application builds LLM prompts using external input, but the structure fails to distinguish the line between user input and system instructions.

Impact

The consequences are entirely contextual, depending on the system that the model is integrated into. Leakage of sensitive information, remote code execution, execution of unauthorized actions, etc.

Recommendation

- Ensure proper sanitization of user-controllable input.
- User-controllable input must be identified as untrusted and potentially dangerous.
- Separate instructions from user input.
- Audit interactions.
- The model could be fine-tuned to better control and neutralize potentially dangerous inputs.
- Limit critical functions exposed to the model.

Threat

Authenticated attacker from the Internet.

Expected Remediation Time

⌚ 60 minutes.

Score

Default score using CVSS 3.1. It may change depending on the context of the src.

Base

  • Attack vector: N
  • Attack complexity: L
  • Privileges required: L
  • User interaction: N
  • Scope: U
  • Confidentiality: N
  • Integrity: L
  • Availability: N

Temporal

  • Exploit code maturity: U
  • Remediation level: O
  • Report confidence: C

Result

  • Vector string: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N/E:U/RL:O/RC:C
  • Score:
    • Base: 4.3
    • Temporal: 3.8
  • Severity:
    • Base: Medium
    • Temporal: Low

Score 4.0

Default score using CVSS 4.0. It may change depending on the context of the src.

Base 4.0

  • Attack vector: N
  • Attack complexity: L
  • Attack Requirements: N
  • Privileges required: L
  • User interaction: N
  • Confidentiality (VC): N
  • Integrity (VI): L
  • Availability (VA): N
  • Confidentiality (SC): N
  • Integrity (SI): N
  • Availability (SA): N

Threat 4.0

  • Exploit maturity: U

Result 4.0

  • Vector string: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N/E:U
  • Score:
    • CVSS-BT: 1.3
  • Severity:
    • CVSS-BT: Low

Compliant code

Non compliant code

Requirements

Fixes

Free trial message
Free trial
Search for vulnerabilities in your apps for free with Fluid Attacks' automated security testing! Start your 21-day free trial and discover the benefits of the Continuous Hacking Essential plan. If you prefer the Advanced plan, which includes the expertise of Fluid Attacks' hacking team, fill out this contact form.