Agentic Workflow Injection is a new injection vulnerability class in LLM-augmented GitHub Actions, with two patterns (P2A and P2S) detected via the TaintAWI tool yielding 496 confirmed exploitable instances across 13,392 workflows.
Weber, Large language models as software components: A taxonomy for LLM- integrated applications (2024)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
PRJA achieves 83.6% average success injecting harmful content into LRM reasoning chains on five QA datasets without altering final answers.
Agentic Business Process Management reframes BPM around autonomous agents that must exhibit framed autonomy, explainability, conversational actionability, and self-modification to keep their actions aligned with organizational objectives.
Qualitative study of 20 users of integrated browser conversational AI found that citations raise trustworthiness without verification and that users apply existing LLM and search perceptions to prompting strategies.
citing papers explorer
-
Beliefs and Misconceptions around Integrated Conversational AI
Qualitative study of 20 users of integrated browser conversational AI found that citations raise trustworthiness without verification and that users apply existing LLM and search perceptions to prompting strategies.