Explore/agent app/From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
F

Pritam Dash, Tongyu Ge, Aditi Jain, Tanmay Shah, Zhiwei Shang/From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM AgentsUnknown

Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory introduces the risk of memory poisoning, where a single adversarial memory write can exert long-term influence over agent behavior. We present a systematic study of memory poisoning in LLM-based agents. We identify four memory write channels and nine structural vulnerabilities in model capabilities, system prompt design, and agent system architecture that make these channels exploitable. Based on these vulnerabilities, we develop a taxonomy of six classes of memory poisoning attacks. Furthermore, we design MPBench -- a benchmark for evaluating memory poisoning attacks, and show that agents designed to write and retrieve memory more aggressively are more exploitable. We also show that existing prompt injection defenses fail to cover memory poisoning attacks. Our findings provide a foundation for understanding and mitigating memory poisoning attacks against AI agents.

agent app
GitHubCompare
Refreshed 1mo ago
OverviewActivity52wAlternativesDocs
Stars0
Forks0
HF Downloads—30d
Last commit—
Refreshed1mo ago
Project healthUnknownNo activity data.
Production readinessResearch / EarlyBest for exploration and prototyping.
Risk notesUnknown licenseVerify license before production use.
AgentHub Score
55 / 100
Composite score from 6 signals. How we score →
Active project
55Score
Growth
40C
Activity
30C
Documentation
70C+
Maturity
45C
Community
42C
Production
58C
GitHub stars · 1 days observed0 not enough history
snapshots
Repository activity · 1 days observedReal snapshots from pushed_at
inactivepushed
2026-07-262026-07-28
Practical assessment
Should you use it?

✓ Best for

  • Research and experimentation
  • Prototype development
  • Learning agentic patterns

◎ Strengths

  • Active community
  • Open source
  • Well-documented API

✕ Not ideal for

  • Untested at scale without validation
  • Teams without AI/ML expertise

⚠ Watch-outs

  • Review changelog before updating
  • Verify license for commercial use
Technical details
What's inside
Language—
License—
Sourcearxiv
Open source✗ No
Commercial use—
Docs—
Demo—

AgentHub Score

55
Score 55/100
Below average

Alternatives

A
ai-agents-for-beginners
70.5k · agent app
95
V
Vibe-Trading
28.1k · agent app
95
A
ai-website-cloner-template
30.4k · agent app
88
R
rowboat
16.8k · agent app
87Compare all →

Recent activity

Latest commit ——
Indexed by AgentHub crawler1mo ago
Monitor for new releasesongoing