Prompt injection robustness against adaptive attackers, coding (Anthropic)
Claude Opus 4.6 0% leads since February 2026
Only in system cards Coding agents face indirect prompt injections crafted by an adaptive attacker. Score is attack success rate.
Anthropic uses Gray Swan's Shade adaptive attacker for this surface. Reported at 1 and many attempts.
- Made by
- Anthropic
- Released
- November 2025
- Kind
- Jailbreaks and prompt injection
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Strongest model tested
- Claude Fable 5.2 #1 on the capability index
- Last in a system card
- November 2026
- Last model added
- November 2026
14
Models scored in lab cards
14
System cards report it, from 1 lab
3 models share the top score of 0%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Claude Opus 4.6 0%
- 2 Claude Sonnet 4.6 0%
- 3 Claude Mythos Preview 0%
- 4 Claude Haiku 5.5 0.08%
- 5 Claude Opus 4.5 0.30%
- 6 Claude Sonnet 5 0.31%
- 7 Claude Fable 5 0.45%
- 8 Claude Opus 5 0.56%
- 9 Claude Opus 4.7 2.34%
- 10 Claude Sonnet 5.5 3.01%
- 11 Claude Opus 4.8 7.03%
- 12 Claude Fable 5.1 9.26%
- 13 Claude Opus 5.5 54.6%
- 14 Claude Fable 5.2 89.8%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 0% | Feb 2026 | Lab model card | |
| 2 | Claude Sonnet 4.6 | 0% | Feb 2026 | Lab model card | |
| 3 | Claude Mythos Preview | 0% | Apr 2026 | Lab model card | |
| 4 | Claude Haiku 5.5 | 0.08% | Oct 2026 | Lab model card | |
| 5 | Claude Opus 4.5 | 0.30% | Nov 2025 | Lab model card | |
| 6 | Claude Sonnet 5 | 0.31% | Jun 2026 | Lab model card | |
| 7 | Claude Fable 5 | 0.45% | Jun 2026 | Lab model card | |
| 8 | Claude Opus 5 | 0.56% | Jul 2026 | Lab model card | |
| 9 | Claude Opus 4.7 | 2.34% | Apr 2026 | Lab model card | |
| 10 | Claude Sonnet 5.5 | 3.01% | Sep 2026 | Lab model card | |
| 11 | Claude Opus 4.8 | 7.03% | May 2026 | Lab model card | |
| 12 | Claude Fable 5.1 | 9.26% | Sep 2026 | Lab model card | |
| 13 | Claude Opus 5.5 | 54.6% | Sep 2026 | Lab model card | |
| 14 | Claude Fable 5.2 | 89.8% | Nov 2026 | Lab model card |
2 models have held number one in labs’ own numbers since its release in November 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Anthropic
Source: Labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Reported by the lab in its model card
Best so far
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
14 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 9, 2026 | Claude Fable 5.2 system card | 89.8 | Shade indirect prompt injection in coding, attempt-level attack success rate without prompt injection probes, adaptive thinking, with cyber classifier fallbacks, 40/40 scenarios. With probes 28.16%. Of valid responses, 99.46% were served by Opus 4.8 (Table 5.2.2.1.A) | Robustness |
| Oct 7, 2026 | Claude Haiku 5.5 system card | 0.08 | Shade adaptive attacker, coding, attempt-level attack success rate without safeguards, 6/40 scenarios. With probes 0% (Table 5.2.2.1.A) | Robustness |
| Sep 28, 2026 | Claude Sonnet 5.5 system card | 3.01 | Shade adaptive attacker in coding, attempt-level attack success rate without safeguards, with thinking, 16/40 scenarios (2.63% with probes) (Table 5.2.2.1.A) | Robustness |
| Sep 22, 2026 | Claude Opus 5.5 system card | 54.6 | Shade adaptive attacker in coding, attempt-level attack success rate without safeguards, with thinking, 37/40 scenarios (11.13% and 36/40 with probes), lower is better (Table 5.2.2.1.A) | Robustness |
| Sep 1, 2026 | Claude Fable 5.1 system card | 9.26 | Shade indirect prompt injection in coding, attempt-level attack success rate, with thinking, without PI probes, including cyber classifier fallback to Opus 4.8 (no attacks succeeded on the 369 requests Fable 5.1 answered directly); 31/40 scenarios; 2.05% with PI probes; new stronger Shade attacker 56.87% (12.80% with probes) (Tables 5.2.2.1.A and 5.2.2.1.B) | Robustness |
| Jul 24, 2026 | Claude Opus 5 system card | 0.56 | Shade adaptive attacker in coding, attempt-level attack success rate without safeguards, with thinking, 13/40 scenarios (0.18% and 4/40 with probes), lower is better (Table 5.2.2.1.A) | Robustness |
| Jun 30, 2026 | Claude Sonnet 5 system card | 0.31 | Shade adaptive attacker in coding, attempt-level attack success rate without safeguards, with thinking, 7/40 scenarios (0.29% without thinking. 0.09% with safeguards), lower is better (Table 5.2.2.2.A) | Robustness |
| Jun 9, 2026 | Claude Fable 5 system card | 0.45 | Shade indirect prompt injection in coding, attempt-level attack success rate without safeguards, with thinking, 40 scenarios x200 attempts, row labeled Mythos 5, 8/40 scenarios broken; with safeguards 0.41% and 11/40, lower is better (Table 5.2.2.1.A) | Robustness |
| May 28, 2026 | Claude Opus 4.8 system card | 7.03 | Shade adaptive attacker in coding, 40 scenarios, single-attempt attack success rate without safeguards, with thinking (200 attempts 57.5%. With safeguards 2.09% and 37.5%. Without thinking 17.44%), lower is better (Table 5.2.2.2.A) | Robustness |
| Apr 16, 2026 | Claude Opus 4.7 system card | 2.34 | Shade attacks in coding, with thinking, without safeguards, 1 attempt. 200 attempts 60.0. Without thinking 10.43 and 92.5. With safeguards 0.43 and 25.0 (Table 5.2.2.1.A) | Robustness |
| Apr 7, 2026 | Claude Mythos Preview system card | 0 | Shade attacks in coding, extended thinking, without safeguards, 1 attempt, lower is better; 0.0 at 200 attempts, standard thinking 0.03 and 2.5 (Table 8.3.2.2.1.A) | Robustness |
| Feb 17, 2026 | Claude Sonnet 4.6 system card | 0 | Shade attacks in coding, extended thinking, without safeguards, 1 attempt; 0.0 at 200 attempts, standard thinking 0.1 and 7.5 (Table 5.2.2.1.A) | Robustness |
| Feb 5, 2026 | Claude Opus 4.6 system card | 0 | Shade adaptive prompt injection in coding, attack success rate, extended thinking, without safeguards, 1 attempt, lower is better; 0.0 in every condition including 200 attempts (Table 5.2.2.1.A) | Robustness |
| Nov 24, 2025 | Claude Opus 4.5 system card | 0.3 | Shade adaptive indirect prompt injection, coding, attack success rate at 1 attempt, extended thinking, no safeguards, lower is better (Table 5.2.2.1.A; 10.0% with 200 attempts, standard thinking 0.7% and 17.5%) | Robustness |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0% - DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics.
Muse Spark 1.2 88.4% - Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%