Malicious Skills induce coding agents to hallucinate and import attacker-controlled packages at high rates while evading detection.
Skills | claude
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
Malicious Skills induce coding agents to hallucinate and import attacker-controlled packages at high rates while evading detection.