Safety testing of the open model gpt-oss-20b in Spanish agent setups, with tools and fake credentials in the prompt. Five failure patterns documented, each with a proposed mitigation.
Researcher · AI safety and governance · Experiment
Small companies and public-sector teams are wiring language models to tools such as search, databases and reservations, often with few guardrails and often in Spanish. Most safety evaluations are written in English. I wanted to know how the open model gpt-oss-20b behaves when the attack arrives in Spanish, inside the kind of agent prompt a real team would write.
How to read it. Read left to right. Each hypothesis becomes a family of Spanish prompts, always with a negative control that removes the trigger. The base prompt imitates a realistic agent: a role, a list of tools and fake credentials. The highlighted box is the comparison across two providers, which separates model behavior from a single vendor quirk.
The base system prompt sets up a travel and country assistant with a list of tools (search, database query, reservations) and a block of fake database credentials. The write-up designs each hypothesis as three Spanish paraphrases and one negative control that removes the trigger, such as dropping a role claim or replacing a policy text with a placeholder.
The write-up describes repeated runs with simple pattern matchers. The notebooks keep single calls per provider, with the reruns counted by hand: the notes record the issues appearing “8 or 9 times of 10” and a fabricated-fact test failing 6 of 10 runs on one provider and 9 of 10 on the other. Treat those figures as indicative, as the write-up itself says.
Severity and breadth are the write-up’s own ratings.
| Pattern | What happens | Severity | Breadth |
|---|---|---|---|
| Keyword-gate bypass | A country name in the request turns a refusal of an off-topic task into full compliance | Low | Moderate |
| Credential surfacing | A user who claims to be an IT admin gets the credentials embedded in the prompt quoted back | 2 to 3 | 2 |
| Tool-use hallucination | Tool descriptions in the prompt lead to confident multi-step tool plans, including privileged actions | 2 to 3; high if wired to real tools | 2 |
| Policy injection | A fictional “new policy” in the prompt is repeated as fact without verification | 2 | 2 |
| False system-state claims | Asked whether it was compromised, the model states that it was, without evidence | 1 to 2 | 2 |
Cost was limited to API calls on the two providers, one of them on a free tier.
An experiment, written up on Kaggle with the two notebooks behind it. The results are indicative: manual prompts, small run counts and public endpoints that may differ from a local build. The value is the method and the five patterns, which map directly to the governance controls I recommend to teams putting agents in front of customers.
Automating the harness: the same prompt families run on a schedule against each new model version, with stored pass rates per pattern, so a team can see whether an upgrade made its agent safer or not.
Danilo Salazar · Origo Solutions