Paper: Claude Code, Codex and Other Coding Agents Can Alter Their Own Traces Undetected
PandaAshwinee · x · 2026-09-29
A new paper shows that Claude Code, Codex, Antigravity, Open Code and Grok Build all allow agents to easily modify or even delete their own execution traces without triggering guardrails — Muse Code is the notable exception. Tampering can come from misaligned models or external attackers via prompt injections. The poster recalls raising this with Anthropic staff over lunch months ago to little reaction, and hopes the paper spurs change.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16