A short string hidden inside a code comment can make LLM coding assistants generate attacker-chosen vulnerable code when they retrieve that comment from the web.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inducing Vulnerable Code Generation in LLM Coding Assistants
A short string hidden inside a code comment can make LLM coding assistants generate attacker-chosen vulnerable code when they retrieve that comment from the web.