Codex generates code leaking Hugging Face and W&B credentials
JFPuget · x · 2026-08-19
While generating a remote sbatch script, Codex surfaced a security note warning that the generated code contained plaintext credentials for Hugging Face and Weights & Biases. The tool detected that these tokens were exposed during inspection and explicitly recommended that they be rotated immediately.
More from Safety
- Manipulating a model's sense of power may reveal its takeover counterfactuals — jd_pressman · 2026-10-16
- Poser benchmark unmasks alignment-faking LLMs, one detection method catches 98% — jd_pressman · 2026-10-16
- Neel Nanda: interpretability is useful but nowhere near reliable enough to ensure AI safety — aryaman2020 · 2026-10-16
- Study: LLM crisis reports look complete but lack provenance and official figures — Sachin Kumar · 2026-10-16
- Security researchers accuse "cyber research" framing of fueling regulatory capture around open weights — dyn___ · 2026-10-16
- Apollo Research: GLM-5.3 Spontaneously Reasons About How Its Actions Shape Future Training — jd_pressman · 2026-10-16