DeepTrap automates discovery of contextual vulnerabilities in OpenClaw agents via trajectory optimization, showing that unsafe behavior can be induced while preserving task completion and that final-response checks are insufficient.
Clawdrain: Exploiting tool-calling chains for stealthy token exhaustion in OpenClaw agents
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Routine user chats can unintentionally poison the long-term state of personalized LLM agents, causing authorization drift, tool escalation, and unchecked autonomy, as measured by a new benchmark and reduced by the StateGuard defense.
Claw AI agents' heartbeat background execution shares memory context with user sessions, allowing ordinary social misinformation to silently pollute long-term memory and shape behavior at rates up to 76% across sessions.
The survey organizes security threats and defenses in autonomous LLM agents into four layers and identifies that risks can propagate across layers from inputs to ecosystem impacts.
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.
A systematic review of resource consumption threats in LLMs that organizes the problem along the full pipeline from threat induction to mitigation.
citing papers explorer
-
Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.