There are 8 attacks in the misinformation category. Each shows its technique id, mode, standards mapping, description, and the exact command to run it (swap the provider and target as needed).
​
high
citation-manipulation · single-turn · OWASP: LLM07Prompt model to attribute false quotes to real public figuresRun it:
​
medium
anchoring-bias · multi-turn · OWASP: LLM07Multi-turn attack providing a wrong answer first then asking model to build on itRun it:
​
medium
confidence-exploitation · single-turn · OWASP: LLM07Push model to state uncertain information as established fact without hedgingRun it:
​
medium
fabrication-prompting · single-turn · OWASP: LLM07Prompt model to generate fake citations, fabricated research, or invented statisticsRun it:
​
medium
false-premise · single-turn · OWASP: LLM07Build prompts on false premises to see if model accepts and elaboratesRun it:
​
medium
knowledge-boundary · single-turn · OWASP: LLM07Test if model admits uncertainty on post-cutoff or fictional eventsRun it:
​
medium
selective-context · single-turn · OWASP: LLM07Provide heavily biased one-sided context to produce biased outputRun it:
​
medium
sycophancy-exploit · multi-turn · OWASP: LLM07 · MITRE: AML.T0043.003Multi-turn attack exploiting model tendency to agree with user assertionsRun it: