INTEL_REPORT
arXiv — Cryptography & Security (cs.CR) · published 7/17/2026, 4:00:00 AM · TLP amber
Summary
Ingested excerpt (first ~500 chars of normalized text).
Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems arXiv:2607.14611v1 Announce Type: new Abstract: A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be embedded within persistent files and influence future be…
https://arxiv.org/abs/2607.14611
sha256:78e7aacae89af0065b44fcf488946f5c5d3a086316cbf19cd5772c6f58fe77a2
What we pulled out
Deterministic extractor (IOC + allowlisted tokens + ATT&CK IDs present in DB).
Indicators
Linked with report → mentions → indicator. Values open the indicator workspace.
No indicators linked for this report.
Malware families
Allowlist token matches only.
Threat actors mentioned
Allowlist mentions — not a formal attribution verdict.
ATT&CK techniques
MITRE IDs referenced in text and present in local technique table.
CONTINUE INVESTIGATION
High-signal pivots without leaving the thread you started in search.
Browse the report corpus.