AI Application Security(LLM)

[TimmyBugcrowd]

Adding:

Application Level DoS - Excessive Resource Consumption - Injection (Prompt) - Varies
AI Application Security - Large Language Model (LLM) Security - Prompt Injection - P1
AI Application Security - Large Language Model (LLM) Security - LLM Output Handling - P1
AI Application Security - Large Language Model (LLM) Security - Training Data Poisoning - P1
AI Application Security - Large Language Model (LLM) Security - Excessive Agency/Permission Manipulation - P2

[drunkrhin0]

@TimmyBugcrowd the ID's don't match my branch here. Unsure of if they need to be identical.

https://github.com/bugcrowd/vulnerability-rating-taxonomy/tree/LLM-VRT-Additions

[drunkrhin0]

Additionally I'd suggest kicking off CVSSv4 ratings since AI is more advanced than what the CVSS 3.1 maturity model was intended for

[trimkadriu]

lgtm