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.
Demystifying rce vulnerabilities in llm-integrated apps
5 Pith papers cite this work, alongside 17 external citations. Polarity classification is still indexing.
5
Pith papers citing it
17
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
LogicHunter combines specification-driven test generation with a ReAct-based agentic oracle to discover 40 previously unknown bugs in LangChain, LlamaIndex, and CrewAI, achieving 91.17% oracle precision.
AgentFlow builds a framework-agnostic Agent Dependency Graph from agent program source code to support static analyses such as BOM generation and prompt-to-tool risk detection, evaluated on 5,399 real programs across five frameworks.
Measurement of 688 AI infra repositories shows frequent overlapping vulnerable patterns, and INFRASCOPE detects over 20 variants including 11 acknowledged and 4 with new CVEs.
PQC software implementation is a socio-technological problem whose challenges span interdependent Human, Organisation and Technology factors; the PQC-HOT model organises them for analysis and planning.
citing papers explorer
-
Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
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.
-
LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle
LogicHunter combines specification-driven test generation with a ReAct-based agentic oracle to discover 40 previously unknown bugs in LangChain, LlamaIndex, and CrewAI, achieving 91.17% oracle precision.
-
AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs
AgentFlow builds a framework-agnostic Agent Dependency Graph from agent program source code to support static analyses such as BOM generation and prompt-to-tool risk detection, evaluated on 5,399 real programs across five frameworks.
-
Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection
Measurement of 688 AI infra repositories shows frequent overlapping vulnerable patterns, and INFRASCOPE detects over 20 variants including 11 acknowledged and 4 with new CVEs.
-
SoK: Post-Quantum Cryptography Implementation in Software: Approaches, Challenges and the PQC-HOT Framework
PQC software implementation is a socio-technological problem whose challenges span interdependent Human, Organisation and Technology factors; the PQC-HOT model organises them for analysis and planning.