Skip to main content

CCC.GenAI.TH01: Prompt Injection

Threat ID:CCC.GenAI.TH01
Title:Prompt Injection
Description:

Prompt injection may occur when crafted input is used to manipulate the GenAI model's behaviour, resulting in the generation of harmful or unintended outputs. Prompt injection can be either direct (performed via direct interaction with the model) or indirect (performed via external sources ingested by the model). Both text-based and multi-modal prompt injection is possible.

Related Capabilities

IDTitleDescription
CCC.Core.F14API AccessThe service exposes a port enabling external actors to interact programmatically with the service and its resources using HTTP protocol methods such as GET, POST, PUT, and DELETE.
CCC.GenAI.F15Text-Based PromptsAbility to input prompts in plain text.
CCC.GenAI.F16Structured PromptsAbility to provide structured input such as JSON as prompts.
CCC.GenAI.F17Contextual PromptsAbility to provide context or background information within the prompt to guide the response.
CCC.GenAI.F18Interactive PromptsAbility to use conversational prompts to create interactive dialogues.
CCC.GenAI.F19Image-Based PromptsAbility to input an image as a prompt to generate a response.
CCC.GenAI.F20Custom Template PromptsAbility to define custom templates or structures for prompts to standardize interactions with the models.
CCC.GenAI.F21Generate ContentAbility to generate a response given a foundation model, parameter values, and a prompt.
CCC.GenAI.F24Content ModerationEnsure the service detects and filters abusive, harmful, and sensitive information to ensure responsible and safe use of the service.

External Mappings

Reference IDEntry IDStrengthRemarks
FINOS-AIGF
AIR-SEC-010
0
Prompt Injection
SAIF
PIJ
0
Prompt Injection
SAIF
MEV
0
Model Evasion
OWASP-LLM-TOP10
LLM01:2025
0
Prompt Injection
MITRE-ATLAS
AML.T0051
0
LLM Prompt Injection
MITRE-ATLAS
AML.T0051.000
0
LLM Prompt Injection: Direct
MITRE-ATLAS
AML.T0051.001
0
LLM Prompt Injection: Indirect
MITRE-ATLAS
AML.T0065
0
LLM Prompt Crafting
MITRE-ATLAS
AML.T0068
0
LLM Prompt Obfuscation
MITRE-ATLAS
AML.T0054
0
LLM Jailbreak

Controls

IDTitleObjectiveControl FamilyThreat MappingsGuideline MappingsAssessment Requirements
CCC.GenAI.C01Model Input Filtering and SanitisationInspect and validate input before it is passed to a GenAI model in order to filter or sanitise adversarial queries and prevent sensitive data leakage. Data
2
8
2
CCC.GenAI.C02Model Output Filtering and SanitisationInspect and validate GenAI model output before passing it to users, applications or plugins in order to filter or sanitise insecure or unreliable output and prevent sensitive data leakage. Data
5
7
2
CCC.GenAI.C08Quality Control and Red TeamingEstablish a formal program for quality evaluation and adversarial testing (red teaming) to ensure GenAI system meet all business, quality, security and compliance requirements before getting deployed into production environments. Model Assurance and Evaluation
5
5
2