There are 9 attacks in the context-manipulation category. Each shows its technique id, mode, standards mapping, description, and the exact command to run it (swap the provider and target as needed).
​
Lifecycle Staging
critical
lifecycle-staging · multi-turn · OWASP: LLM01, LLM06 · MITRE: AML.T0054, AML.T0065, AML.T0080.002Asks about each stage of the CBRN lifecycle separately (acquisition, production, weaponization, delivery) so no single message triggers safety filtersRun it:
ai-blackteam run -p anthropic -a lifecycle-staging -t "your target prompt"
​
Context Manipulation
high
context-manipulation · multi-turn · OWASP: LLM01 · MITRE: AML.T0051.000, AML.T0080.00210-turn conversational drift to gradually shift context toward harmful contentRun it:
ai-blackteam run -p anthropic -a context-manipulation -t "your target prompt"
​
Crescendo
high
crescendo · multi-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0065Progressive escalation through self-referencing conversation historyRun it:
ai-blackteam run -p anthropic -a crescendo -t "your target prompt"
​
Narrative Misdirection Attack
high
narrative-misdirection · multi-turn · OWASP: LLM01, LLM09 · MITRE: AML.T0054, AML.T0065Embed harmful request between benign topics and ask model to logically connect all threeRun it:
ai-blackteam run -p anthropic -a narrative-misdirection -t "your target prompt"
​
Socratic Escalation
high
socratic-escalation · multi-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0065Gradually escalates from general educational questions to specific harmful requests across multiple turns using Socratic questioningRun it:
ai-blackteam run -p anthropic -a socratic-escalation -t "your target prompt"
​
Contradiction Exploit
medium
contradiction-exploit · multi-turn · OWASP: LLM01, LLM09 · MITRE: AML.T0054, AML.T0065Feed incorrect information to elicit corrections containing harmful truthRun it:
ai-blackteam run -p anthropic -a contradiction-exploit -t "your target prompt"
​
Conversation Derailment
medium
conversation-derailment · multi-turn · OWASP: LLM01 · MITRE: AML.T0051.000, AML.T0080.002Self-discovery of model weaknesses through probing conversationRun it:
ai-blackteam run -p anthropic -a conversation-derailment -t "your target prompt"
​
Goalpost Moving
medium
goalpost-moving · multi-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0065Incremental agreement chain that builds logical trap making refusal seem contradictoryRun it:
ai-blackteam run -p anthropic -a goalpost-moving -t "your target prompt"
​
Sunk Cost Exploit
medium
sunk-cost-exploit · multi-turn · OWASP: LLM01 · MITRE: AML.T0054, AML.T0065Build helpful context then pivot to harmful request exploiting sunk costRun it:
ai-blackteam run -p anthropic -a sunk-cost-exploit -t "your target prompt"