LLM Agents Can Easily Tamper with Their Own Traces
These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail to enforce this boundary. All tested harnesses, except Muse Code, allowed agents to delete their traces when asked, without triggering monitor guardrails.
- ▪These analyses assume that LLM agents cannot tamper with their own execution traces.
- ▪We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail to enforce this boundary.
- ▪All tested harnesses, except Muse Code, allowed agents to delete their traces when asked, without triggering monitor guardrails.
2 outlets in our directory ran this story, first to last over 1 hour. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ The Perfect Crime: LLM Agents Can Easily Tamper with Their Own Traces — Perfect-crime
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,577 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2609.30266 |
| Publication time | Sun, 27 Sep 2026 05:07:08 +0000 |
| Retrieval time | 2026-09-27T05:15:40.930Z |
| Last seen | 2026-09-27T05:15:40.930Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | i4GnmBanWhUW · 3 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Cryptography and Security arXiv:2609.30266 (cs) [Submitted on 24 Sep 2026] Title:LLM Agents Can Easily Tamper With Their Own Traces Authors:Jeremy Qin, David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Ameya Prabhu, Maksym Andriushchenko View a PDF of the paper titled LLM Agents Can Easily Tamper With Their Own Traces, by Jeremy Qin and 5 other authors View PDF HTML (experimental) Abstract:Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents such as Claude Code, Codex, Antigravity, Open Code and Grok Build fail to enforce this boundary.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
