SkillHarm benchmark shows current AI agents are vulnerable to lifecycle-aware skill poisoning with success rates up to 86.3% for fixed-payload attacks and 69.3% for self-mutating attacks.
Distractor injection attacks on large reasoning models: Characterization and defense,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Adversaries can use crafted scene text to trigger overthinking in LVLM-based robots, producing transferable slowdowns up to 6.96x latency amplification.
citing papers explorer
-
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
SkillHarm benchmark shows current AI agents are vulnerable to lifecycle-aware skill poisoning with success rates up to 86.3% for fixed-payload attacks and 69.3% for self-mutating attacks.
-
Overthink-Triggered Slowdown Attacks on LVLM-Based Robotic Systems
Adversaries can use crafted scene text to trigger overthinking in LVLM-based robots, producing transferable slowdowns up to 6.96x latency amplification.